© 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. 91870
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    PreferredItem
    -0.57
    المناصب
    -0.54
    PageContext
    -0.51
    buttonBar
    -0.51
    PyExc
    -0.50
    исленность
    -0.49
    Rhestr
    -0.49
    kable
    -0.48
     quæ
    -0.47
    edia
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    SequentialGroup
    0.54
    ledem
    0.52
     Gets
    0.49
     Performs
    0.47
    EClass
    0.47
    bigoplus
    0.46
    tics
    0.46
     onAnimation
    0.46
     isNameExpr
    0.45
    Activations Density 0.002%

    No Known Activations