© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11624
    Prev
    Next
    INDEX
    Explanations

    words related to aggression and friendliness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asciug
    -0.78
    issipp
    -0.73
    <h5>
    -0.69
     inset
    -0.68
    awtextra
    -0.68
    Moments
    -0.68
    zeug
    -0.67
    setof
    -0.67
    gefügt
    -0.67
     limone
    -0.66
    POSITIVE LOGITS
     agres
    1.00
     aggres
    0.94
     aggressive
    0.92
     hostile
    0.92
     hostility
    0.91
     aggressiveness
    0.89
    aggressive
    0.85
     friendly
    0.84
     friendliness
    0.82
     Friendly
    0.82
    Activations Density 0.012%

    No Known Activations