© 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. 95361
    Prev
    Next
    INDEX
    Explanations

    agency

    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
    drawal
    -0.85
    참고
    -0.82
     Jefus
    -0.82
    Pautan
    -0.82
    IBLIO
    -0.81
    ADRID
    -0.79
    出版年
    -0.79
    ^(@)
    -0.79
    verwijspagina
    -0.77
    
    -0.77
    POSITIVE LOGITS
    ’
    0.52
     and
    0.48
     I
    0.47
    ,
    0.47
    <strong>
    0.46
     to
    0.46
     
    0.46
    .
    0.45
    ar
    0.45
     O
    0.45
    Activations Density 1.646%

    No Known Activations