© 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. 1-CLT-HP
    7. 15191
    Prev
    Next
    INDEX
    Explanations

    perennial

    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
     Perennial
    -0.84
    awtextra
    -0.80
     perennial
    -0.77
    sidemargin
    -0.73
     nahilalakip
    -0.73
    featureID
    -0.69
    ⓧ
    -0.69
     autorytatywna
    -0.68
    bootstrapcdn
    -0.65
     snippetHide
    -0.64
    POSITIVE LOGITS
    gorithm
    0.56
     itſelf
    0.56
     Majefty
    0.54
     purpoſe
    0.51
    erved
    0.50
     getClient
    0.50
     Muses
    0.50
     alignItems
    0.48
    âmica
    0.48
    AILED
    0.48
    Activations Density 0.057%

    No Known Activations