© 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. 92133
    Prev
    Next
    INDEX
    Explanations

    of

    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
    PreferredItem
    -0.52
    ☚
    -0.51
    ůj
    -0.51
    migrationBuilder
    -0.49
    patch
    -0.49
     patch
    -0.47
     hạn
    -0.46
    ystis
    -0.46
    gpt
    -0.46
     bifurcation
    -0.45
    POSITIVE LOGITS
    ISupport
    0.59
    ьаж
    0.58
     continúas
    0.54
    ientí
    0.54
     onstage
    0.54
     humaine
    0.54
    criture
    0.52
    
    0.52
    zarchiwizowane
    0.51
     segíts
    0.51
    Activations Density 0.001%

    No Known Activations