© 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. 9734
    Prev
    Next
    INDEX
    Explanations

    Openings and flows

    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
    elemField
    -0.74
    -------------</
    -0.69
     Emits
    -0.69
    LEncoder
    -0.68
    phinx
    -0.67
    ंदीखरीदारी
    -0.66
    enapa
    -0.64
    </tfoot>
    -0.64
     nitrite
    -0.63
    fjspx
    -0.62
    POSITIVE LOGITS
    oredCriteria
    0.42
    Jeografia
    0.38
    Shal
    0.37
    LookAnd
    0.35
     aspetto
    0.35
    toplasm
    0.34
    al
    0.34
     ты
    0.34
    ukkah
    0.34
    multicolumn
    0.33
    Activations Density 0.064%

    No Known Activations