© 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. 1-CLT-HP
    7. 15521
    Prev
    Next
    INDEX
    Explanations

    BR

    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
     meant
    -0.63
    ArrowToggle
    -0.56
     mev
    -0.50
    meant
    -0.48
     PP
    -0.48
    peh
    -0.44
     ché
    -0.43
     gynhyrchwyd
    -0.42
    JsonProperty
    -0.41
    cplusplus
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    BASELINE
    0.62
    Personensuche
    0.60
     morire
    0.59
    SourceChecksum
    0.57
     dénon
    0.57
    tagHelperRunner
    0.57
     chré
    0.56
     allAfrica
    0.56
    InjectAttribute
    0.56
    Activations Density 0.030%

    No Known Activations