© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74507
    Prev
    Next
    INDEX
    Explanations

    scientific articles

    np_max-act-logits · 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
    WireFormatLite
    -1.02
    expandindo
    -0.85
    Personendaten
    -0.83
     InputDecoration
    -0.82
    ReusableCell
    -0.81
     resourceCulture
    -0.80
     ब्रेकडाउन
    -0.77
     CURIAM
    -0.75
     Administrativna
    -0.74
    MLLoader
    -0.74
    POSITIVE LOGITS
     Vors
    0.46
    StreetMap
    0.43
     Grunde
    0.43
    o
    0.40
    io
    0.39
    CancelButton
    0.39
    groupe
    0.38
    IO
    0.38
    groups
    0.38
     Staf
    0.38
    Activations Density 0.002%

    No Known Activations