© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11025
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific action taken out of fear or urgency

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.17
    0.5%
    897
    +0.12
    0.4%
    1334
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.17
    0.04
    1557
    +0.12
    0.03
    1334
    +0.10
    0.03
    Negative Logits
    Glej
    -0.47
     deluded
    -0.45
     Relaxed
    -0.45
     unspeak
    -0.44
     eqn
    -0.43
     प्रत्य
    -0.43
     Hugs
    -0.43
    Equations
    -0.43
    Cormack
    -0.42
    Slope
    -0.42
    POSITIVE LOGITS
     aspetta
    0.83
     parteci
    0.76
     lapto
    0.74
     krab
    0.73
     tramont
    0.73
     himo
    0.72
     conosce
    0.72
     dichi
    0.72
     esboço
    0.72
     sogni
    0.71
    Activations Density 0.103%

    No Known Activations