© 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. 5-CLT-HP
    7. 4711
    Prev
    Next
    INDEX
    Explanations

    code/licenses

    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
     Or
    -0.56
     OR
    -0.55
     Read
    -0.51
    Or
    -0.47
     En
    -0.46
    lieben
    -0.46
     ModelExpression
    -0.45
     Details
    -0.44
    OR
    -0.43
    ruptedException
    -0.43
    POSITIVE LOGITS
    AnchorStyles
    0.68
    HostException
    0.61
     iota
    0.57
    mappedBy
    0.56
     CURIAM
    0.56
    Famille
    0.56
     GLC
    0.56
    cshtml
    0.56
    !*\
    0.56
     conmigo
    0.55
    Activations Density 0.002%

    No Known Activations