© 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. 0-CLT-HP
    7. 43019
    Prev
    Next
    INDEX
    Explanations

    Base

    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
     base
    -2.00
     Base
    -1.80
    Base
    -1.66
     BASE
    -1.36
    base
    -1.33
    BASE
    -1.02
    getBase
    -0.79
    ベース
    -0.77
    基
    -0.77
     Lee
    -0.76
    POSITIVE LOGITS
     myſelf
    0.86
     Houſe
    0.85
     Efq
    0.82
     vectorielle
    0.81
    StructEnd
    0.80
     doubtnut
    0.78
     Diſ
    0.77
     purpoſe
    0.76
    migrationBuilder
    0.74
     leſs
    0.74
    Activations Density 0.072%

    No Known Activations