© 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. 92070
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    CloseOperation
    -0.90
    GOTREF
    -0.86
    tagHelperRunner
    -0.82
    RenderAtEndOf
    -0.81
    ClientSize
    -0.79
     مشين
    -0.77
     unknownFields
    -0.75
    Erreferentziak
    -0.75
     الحره
    -0.75
    GIVEREF
    -0.74
    POSITIVE LOGITS
     doth
    0.37
     Ad
    0.35
     tru
    0.34
     impati
    0.33
    уза
    0.33
    varargin
    0.33
     berper
    0.32
     End
    0.32
    MENAFN
    0.32
     }}-
    0.32
    Activations Density 0.068%

    No Known Activations