© 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. 95090
    Prev
    Next
    INDEX
    Explanations

    On

    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
     On
    -1.04
    On
    -1.04
     ON
    -0.71
     on
    -0.69
     interfaces
    -0.68
     interface
    -0.67
     Réponses
    -0.65
    OnAdd
    -0.63
    pexpr
    -0.62
    ništvo
    -0.61
    POSITIVE LOGITS
     the
    1.02
    ward
    0.70
     Theſe
    0.70
     behalf
    0.67
     their
    0.66
     a
    0.66
     an
    0.66
     this
    0.63
     your
    0.63
     top
    0.60
    Activations Density 0.052%

    No Known Activations