© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1694
    Prev
    Next
    INDEX
    Explanations

    "

    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
    unik
    -0.57
    󠁢
    -0.56
    ̀i
    -0.56
    ArgsConstructor
    -0.52
    esez
    -0.51
     and
    -0.49
    rawDesc
    -0.49
    írás
    -0.48
    TextBoxColumn
    -0.47
    kulu
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
     StringTokenizer
    0.61
     typelib
    0.60
    ıştır
    0.55
    AddHtmlAttribute
    0.54
     ContentValues
    0.54
     therefrom
    0.53
    InvalidProtocol
    0.53
    IsContent
    0.52
     itinéraires
    0.52
    Activations Density 0.000%

    No Known Activations