© 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. 15313
    Prev
    Next
    INDEX
    Explanations

    of

    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>
    -0.61
     multiple
    -0.42
     of
    -0.42
     "
    -0.42
    eff
    -0.40
     ant
    -0.40
    vin
    -0.40
     vin
    -0.39
    antos
    -0.38
    atern
    -0.38
    POSITIVE LOGITS
     utafitiHapana
    1.02
    ьаж
    1.02
     MainAxisSize
    0.95
     Roskov
    0.95
    
    0.94
     مشين
    0.93
    Hentet
    0.92
    DockStyle
    0.91
    parsedMessage
    0.90
     дописавши
    0.90
    Activations Density 0.019%

    No Known Activations