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

    Neuronpedia

    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. 13674
    Prev
    Next
    INDEX
    Explanations

    phrases related to wheels and tires

    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
    90
    +0.14
    0.6%
    61
    +0.13
    0.5%
    1677
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.14
    0.02
    1677
    +0.13
    0.02
    1691
    +0.13
    0.02
    Negative Logits
     guarante
    -1.11
     secon
    -0.97
     squa
    -0.94
     chrysler
    -0.93
     volunte
    -0.92
     accla
    -0.92
     overla
    -0.91
     intermitt
    -0.90
     maneu
    -0.89
     coö
    -0.89
    POSITIVE LOGITS
     wheel
    1.54
    wheel
    1.46
     Wheel
    1.38
     wheels
    1.35
    Wheel
    1.32
     Wheels
    1.13
    WHEEL
    1.11
    wheels
    1.09
     WHEEL
    1.06
    Wheels
    0.97
    Activations Density 0.090%

    No Known Activations