© 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. 1-CLT-HP
    7. 45816
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -1.01
    DockStyle
    -0.90
    +#+#
    -0.90
    \{\\
    -0.82
     للاسماء
    -0.81
    parsedMessage
    -0.80
    StoryboardSegue
    -0.79
     للمعارف
    -0.78
    CppMethod
    -0.77
    ScopeManager
    -0.77
    POSITIVE LOGITS
     expansion
    0.46
     thought
    0.41
     cross
    0.40
     flow
    0.40
    ij
    0.40
    通し
    0.39
     escape
    0.39
     звука
    0.38
     sound
    0.38
    thought
    0.37
    Activations Density 0.006%

    No Known Activations