© 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. 5-CLT-HP
    7. 3667
    Prev
    Next
    INDEX
    Explanations

    research fields

    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
    Schedules
    -0.50
    ọt
    -0.50
    igia
    -0.48
    práv
    -0.48
    lück
    -0.48
     préparation
    -0.48
    šn
    -0.47
    RAINT
    -0.46
     dégâts
    -0.46
    ventajas
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     ModelExpression
    0.75
     estekak
    0.74
    +#+#
    0.69
     Мексичка
    0.66
     pinulongan
    0.66
     незавершена
    0.65
    IsMutable
    0.65
    دانشنامهٔ
    0.64
     typelib
    0.63
    Activations Density 0.002%

    No Known Activations