© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97161
    Prev
    Next
    INDEX
    Explanations

    established practices

    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
     defaultstate
    -0.58
    TagMode
    -0.52
    AutoScaleMode
    -0.52
     ouverte
    -0.51
     Erişim
    -0.50
    abestanden
    -0.48
    Zusammenfassung
    -0.48
    PageFactory
    -0.48
    >{@
    -0.47
    VersionUID
    -0.47
    POSITIVE LOGITS
     accounts
    0.60
     definitions
    0.57
    astéroïdes
    0.57
     anthropological
    0.56
     counts
    0.56
     ideas
    0.55
     views
    0.54
     portraits
    0.54
    ACGIH
    0.53
     juſ
    0.53
    Activations Density 0.002%

    No Known Activations