© 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. 6923
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection, security, and interests

    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
    1385
    +0.11
    0.3%
    699
    +0.10
    0.3%
    1174
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.11
    0.05
    1174
    +0.10
    0.03
    1352
    +0.09
    0.04
    Negative Logits
    relenting
    -0.72
     gaily
    -0.67
     impra
    -0.66
     withal
    -0.65
    mistak
    -0.64
     disagre
    -0.64
     outlander
    -0.63
     dignité
    -0.62
     heureuse
    -0.61
    YMMV
    -0.60
    POSITIVE LOGITS
     protect
    0.84
     reputa
    0.75
     protecting
    0.74
     protected
    0.74
     inverte
    0.71
     protection
    0.71
     poros
    0.70
     notor
    0.70
    Protect
    0.69
     protects
    0.68
    Activations Density 0.246%

    No Known Activations