© 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. 1-CLT-HP
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    OMO

    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
    er
    -0.50
    amine
    -0.49
    ed
    -0.47
    それとも
    -0.44
     to
    -0.43
    e
    -0.40
     Ame
    -0.40
     rich
    -0.38
    Portale
    -0.37
    ie
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    0.98
    AddTagHelper
    0.86
     autorytatywna
    0.79
     ModelExpression
    0.73
    Hochspringen
    0.72
    RenderAtEndOf
    0.71
     CURIAM
    0.71
     HasFactory
    0.69
    Tikang
    0.68
    roek
    0.67
    Activations Density 0.021%

    No Known Activations