© 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. 0-CLT-HP
    7. 43021
    Prev
    Next
    INDEX
    Explanations

    w

    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
    expandindo
    -0.90
     beginnetje
    -0.82
    TypedDataSet
    -0.80
     Roskov
    -0.69
     المعيارى
    -0.68
    WebElementEntity
    -0.66
    transQ
    -0.65
     autorytatywna
    -0.62
    DebuggerNonUser
    -0.60
    GraphicsUnit
    -0.59
    POSITIVE LOGITS
    <bos>
    1.07
    f
    0.53
    F
    0.52
    หาร
    0.52
    b
    0.51
    B
    0.49
    C
    0.48
    <em>
    0.47
    SC
    0.47
    8
    0.47
    Activations Density 0.000%

    No Known Activations