© 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. 1-CLT-HP
    7. 10976
    Prev
    Next
    INDEX
    Explanations

    Tucker

    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
     виправивши
    -0.60
    DoubleQuotes
    -0.56
    Portail
    -0.54
    ollett
    -0.54
    とめ
    -0.53
    ScopeManager
    -0.53
     Kirke
    -0.52
    reggio
    -0.51
    Sucesor
    -0.51
     Roskov
    -0.49
    POSITIVE LOGITS
    rawDesc
    0.55
    AccessFile
    0.54
     ring
    0.50
    ücksich
    0.49
     חיצוניים
    0.49
    rália
    0.48
     nomine
    0.48
    AndView
    0.47
    sslich
    0.47
     MonoBehaviour
    0.46
    Activations Density 0.018%

    No Known Activations