© 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. 4555
    Prev
    Next
    INDEX
    Explanations

    study

    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
     found
    -0.67
    found
    -0.63
     tells
    -0.61
     expresses
    -0.60
     saw
    -0.60
     wrote
    -0.57
     declares
    -0.57
     finds
    -0.57
     showed
    -0.56
     proves
    -0.56
    POSITIVE LOGITS
     it
    0.66
     propriétaires
    0.59
    RenderAtEndOf
    0.58
    ,
    0.53
     MediatR
    0.52
     seuls
    0.50
    帖最后由
    0.50
     in
    0.50
     proprement
    0.50
     виправивши
    0.50
    Activations Density 0.008%

    No Known Activations