© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91945
    Prev
    Next
    INDEX
    Explanations

    system

    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
    ESSION
    -0.45
    SESSION
    -0.45
     user
    -0.42
     den
    -0.42
     \
    -0.41
     suite
    -0.40
     der
    -0.40
     “
    -0.39
    PACE
    -0.39
     
    -0.39
    POSITIVE LOGITS
     متعلقه
    0.85
     ExecuteAsync
    0.82
    \{\\
    0.82
    MigrationBuilder
    0.81
     MenuView
    0.78
     préfé
    0.77
    InitVars
    0.76
     referenties
    0.75
    хьтан
    0.75
     AssemblyCulture
    0.75
    Activations Density 0.042%

    No Known Activations