© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43277
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.07
    of
    -0.79
     Of
    -0.64
     in
    -0.63
     
    -0.63
     OF
    -0.62
     (
    -0.59
     at
    -0.59
    1
    -0.56
    3
    -0.56
    POSITIVE LOGITS
     purpoſe
    1.01
     itſelf
    0.88
     ſtate
    0.82
     ſmall
    0.82
     ſeveral
    0.81
     greateſt
    0.81
     pleaſure
    0.81
     myſelf
    0.81
     Chriftian
    0.80
    WebElementEntity
    0.80
    Activations Density 0.093%

    No Known Activations