© 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. 4892
    Prev
    Next
    INDEX
    Explanations

    hibian

    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
    Fixed
    -0.52
     fixed
    -0.50
     энциклопедия
    -0.50
    dotta
    -0.48
     fijo
    -0.47
    ingdon
    -0.47
     Fixed
    -0.46
     fix
    -0.45
     deed
    -0.45
    ixe
    -0.43
    POSITIVE LOGITS
    UseVisualStyle
    0.77
    Gambas
    0.65
    المناصب
    0.63
    },{
    0.60
     للاسماء
    0.59
    IUrlHelper
    0.59
    abbix
    0.58
    aarrggbb
    0.57
     isNameExpr
    0.57
    ])->
    0.54
    Activations Density 0.001%

    No Known Activations