© 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. 92784
    Prev
    Next
    INDEX
    Explanations

    too

    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
    ArgsConstructor
    -0.68
    requestCode
    -0.63
    tamol
    -0.62
     betweenstory
    -0.60
     truer
    -0.59
     greets
    -0.56
    ths
    -0.56
     endregion
    -0.56
    demic
    -0.56
    too
    -0.55
    POSITIVE LOGITS
    UNIDENTIFIED
    0.44
     فريبيس
    0.42
    CloseOperation
    0.42
     passive
    0.42
    freep
    0.42
     käyttö
    0.41
    Rhestr
    0.41
    ással
    0.40
     Investigaciones
    0.40
     calm
    0.40
    Activations Density 0.004%

    No Known Activations