© 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. 0-CLT-HP
    7. 93895
    Prev
    Next
    INDEX
    Explanations

    Agency and actions

    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
    Live
    -0.77
     Live
    -0.73
     live
    -0.71
     تضيفلها
    -0.69
    LIVE
    -0.65
     LIVE
    -0.64
    live
    -0.63
     support
    -0.51
    verwijspagina
    -0.51
    WebMethod
    -0.51
    POSITIVE LOGITS
    ThroughAttribute
    0.59
    aurait
    0.58
     the
    0.55
    LookAnd
    0.54
    WebpackPlugin
    0.51
     élas
    0.51
    <bos>
    0.50
    ResumeLayout
    0.49
    igheid
    0.47
    ness
    0.46
    Activations Density 0.045%

    No Known Activations