© 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. 95313
    Prev
    Next
    INDEX
    Explanations

    entry or containment

    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
     Morality
    -0.83
    EndContext
    -0.80
     HasFactory
    -0.79
     Integrity
    -0.75
    contains
    -0.73
     colorés
    -0.72
     sanctity
    -0.70
    inheritDoc
    -0.68
     Contains
    -0.68
     integridad
    -0.68
    POSITIVE LOGITS
     the
    0.79
     a
    0.69
     an
    0.68
     and
    0.60
     just
    0.55
     most
    0.54
     seem
    0.54
     on
    0.53
     it
    0.52
     at
    0.52
    Activations Density 0.027%

    No Known Activations