© 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. 94051
    Prev
    Next
    INDEX
    Explanations

    on

    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
    enderror
    -1.18
     متعلقه
    -1.04
     Wikimedijinoj
    -1.02
     مشين
    -1.00
    帖最后由
    -1.00
    SharedCtor
    -0.95
    tagHelperRunner
    -0.94
    QMetaType
    -0.91
    Datuak
    -0.89
    UnsafeEnabled
    -0.89
    POSITIVE LOGITS
     and
    0.63
     how
    0.54
     on
    0.50
     topics
    0.49
     at
    0.49
    :
    0.48
     of
    0.48
     where
    0.48
    ,
    0.47
     which
    0.45
    Activations Density 0.062%

    No Known Activations