© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41996
    Prev
    Next
    INDEX
    Explanations

    high quality measurements

    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
     calibre
    -0.56
     Babe
    -0.53
     pull
    -0.53
    s
    -0.53
     loving
    -0.52
     caliber
    -0.51
     Tons
    -0.46
     affectionate
    -0.45
     Datas
    -0.44
    gencies
    -0.44
    POSITIVE LOGITS
    IndentedString
    0.75
    DeleteBehavior
    0.71
    存于互联网档案馆
    0.69
    UnsafeEnabled
    0.68
    Pautan
    0.68
    ParallelGroup
    0.66
    photobucket
    0.66
    出版年
    0.65
    EDEFAULT
    0.65
    awtextra
    0.63
    Activations Density 0.146%

    No Known Activations