© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20837
    Prev
    Next
    INDEX
    Explanations

    terms related to attraction and appeal

    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
     jPanel
    -0.73
    <h6>
    -0.69
    Kalb
    -0.67
    次
    -0.66
    <h3>
    -0.64
    pado
    -0.63
    <h5>
    -0.61
    <i>
    -0.61
    Tikang
    -0.60
     Auto
    -0.60
    POSITIVE LOGITS
     Attra
    1.48
     Attraction
    1.47
     attraction
    1.46
     attractiveness
    1.43
     attra
    1.41
    attra
    1.41
    Attra
    1.41
     attractions
    1.33
     attract
    1.31
     attracted
    1.30
    Activations Density 0.016%

    No Known Activations