© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 835
    Prev
    Next
    INDEX
    Explanations

    legal/public records

    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>
    -0.73
    HandlerContext
    -0.72
    expandindo
    -0.69
     ***!
    -0.68
     لينك
    -0.66
    "}")
    -0.66
     smtplib
    -0.63
    Kariera
    -0.62
    zzleHttp
    -0.62
    InjectAttribute
    -0.61
    POSITIVE LOGITS
    STEN
    0.48
     corners
    0.47
     plat
    0.47
     $\#
    0.47
     lands
    0.47
     witness
    0.47
    AndEndTag
    0.46
     Lot
    0.46
     proof
    0.44
     montes
    0.44
    Activations Density 0.016%

    No Known Activations