© 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. 5-CLT-HP
    7. 4521
    Prev
    Next
    INDEX
    Explanations

    code/technical discussions

    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
    TypedDataSet
    -0.76
     autorytatywna
    -0.65
    :✨
    -0.59
    InputBorder
    -0.56
    AnchorStyles
    -0.55
    AndEndTag
    -0.55
     initComponents
    -0.54
    TagMode
    -0.52
    styleType
    -0.52
     дописавши
    -0.51
    POSITIVE LOGITS
    __*/
    0.66
     HttpNotFound
    0.61
     Says
    0.59
     Wants
    0.59
     walks
    0.58
     Gives
    0.57
    Says
    0.56
     decides
    0.56
    .~\
    0.55
     joins
    0.54
    Activations Density 0.004%

    No Known Activations