© 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. 4-CLT-HP
    7. 746
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    SourceChecksum
    -0.81
    +#+#
    -0.77
     незавершена
    -0.77
    ########.
    -0.64
     الرياضيه
    -0.62
    mybatisplus
    -0.59
     users
    -0.56
    FieldBuilder
    -0.56
     EClass
    -0.56
    Users
    -0.55
    POSITIVE LOGITS
     skjer
    0.60
     nameof
    0.53
     namanya
    0.52
     participe
    0.51
    jectures
    0.51
    ograms
    0.51
    ICULO
    0.51
    ipeline
    0.50
    cotch
    0.50
    OrWhiteSpace
    0.49
    Activations Density 0.002%

    No Known Activations