© 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. 14812
    Prev
    Next
    INDEX
    Explanations

    preparation, booking

    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
    parsedMessage
    -0.82
     myſelf
    -0.77
     समीक्षाओं
    -0.73
     bezeichneter
    -0.73
     depositphotos
    -0.73
    ſelves
    -0.70
     BufferedWriter
    -0.67
    bibfield
    -0.67
    ogener
    -0.66
    URLException
    -0.66
    POSITIVE LOGITS
     of
    0.59
    h
    0.50
    ed
    0.49
    e
    0.47
    IPAC
    0.47
     steps
    0.47
    er
    0.47
    al
    0.46
    hard
    0.46
    es
    0.43
    Activations Density 0.007%

    No Known Activations