© 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. 884
    Prev
    Next
    INDEX
    Explanations

    improvement

    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
    UnusedPrivate
    -0.79
    AccessorTable
    -0.63
    ftagPool
    -0.60
     }{@
    -0.58
     kaynağından
    -0.57
    XMLSchema
    -0.57
     <>",
    -0.56
     estimés
    -0.55
    IconModule
    -0.55
     CommonModule
    -0.55
    POSITIVE LOGITS
     on
    0.55
     carry
    0.54
    @[+][
    0.52
    RTSC
    0.49
    ianum
    0.49
    OnError
    0.49
    onk
    0.48
     Administrativna
    0.48
     lend
    0.47
     operate
    0.47
    Activations Density 0.002%

    No Known Activations