© 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. 0-CLT-HP
    7. 94208
    Prev
    Next
    INDEX
    Explanations

    some

    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
    ,
    -0.81
     the
    -0.61
     your
    -0.56
     it
    -0.49
     propres
    -0.49
    ®,
    -0.47
     its
    -0.46
    your
    -0.46
    the
    -0.46
     our
    -0.44
    POSITIVE LOGITS
     fhould
    0.81
    RegressionTest
    0.78
    EndInit
    0.76
    ftagPool
    0.74
     ſhould
    0.73
    Hochspringen
    0.72
    jectures
    0.69
    MigrationBuilder
    0.68
    RenderAtEndOf
    0.67
     ')[
    0.66
    Activations Density 0.063%

    No Known Activations