© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71598
    Prev
    Next
    INDEX
    Explanations

    question words

    np_max-act-logits · 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
    RenderAtEndOf
    -0.95
    UnusedPrivate
    -0.95
     Meksiku
    -0.94
     Efq
    -0.94
    ftagPool
    -0.93
     transfieras
    -0.89
     intStringLen
    -0.88
    oredCriteria
    -0.87
    (!__
    -0.87
    RegistryLite
    -0.84
    POSITIVE LOGITS
     which
    0.52
     Which
    0.49
    which
    0.47
     cuales
    0.45
     who
    0.45
     whom
    0.44
    who
    0.42
    Which
    0.42
     What
    0.40
     hé
    0.40
    Activations Density 0.000%

    No Known Activations