© 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. 5491
    Prev
    Next
    INDEX
    Explanations

    Existence or quantity

    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
     multiple
    -0.51
    '][]
    -0.49
    さら
    -0.49
     partial
    -0.48
     several
    -0.48
     greatly
    -0.47
    tily
    -0.47
     ImportError
    -0.44
     three
    -0.42
    PostBack
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.95
     colgantes
    0.68
    HtmlAttribute
    0.68
    PreExecute
    0.65
     decorativas
    0.64
    antMatchers
    0.64
    XmlAccessType
    0.60
     <=",
    0.60
     decoradas
    0.60
     transfieras
    0.60
    Activations Density 0.002%

    No Known Activations