© 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. 20-CLT-HP
    7. 71779
    Prev
    Next
    INDEX
    Explanations

    various topics

    np_max-act-logits · 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
     مرئيه
    -0.84
    esez
    -0.69
     Efq
    -0.66
     Catawiki
    -0.65
    DockStyle
    -0.64
    AddHtmlAttribute
    -0.63
    eryllium
    -0.62
     Placebo
    -0.61
    zkopf
    -0.61
     Insee
    -0.60
    POSITIVE LOGITS
     actually
    0.72
     not
    0.52
    MigrationBuilder
    0.48
     nowhere
    0.47
    actually
    0.46
     much
    0.46
     pretty
    0.45
    Actually
    0.45
    DatabaseError
    0.44
     simpler
    0.44
    Activations Density 0.000%

    No Known Activations