© 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. 15700
    Prev
    Next
    INDEX
    Explanations

    per

    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
    <bos>
    -0.70
    ,
    -0.57
     (
    -0.52
     in
    -0.47
     to
    -0.46
    -
    -0.45
    ine
    -0.44
    (
    -0.44
    z
    -0.43
     sp
    -0.43
    POSITIVE LOGITS
    
    1.23
    Datuak
    1.11
     Audiodateien
    1.05
     مشين
    0.99
    setVerticalGroup
    0.98
     חיצוניים
    0.98
     autorytatywna
    0.96
     @"/
    0.90
     Normdatei
    0.90
    RegressionTest
    0.89
    Activations Density 0.007%

    No Known Activations