© 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. 5-CLT-HP
    7. 2170
    Prev
    Next
    INDEX
    Explanations

    God

    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
     sent
    -0.45
    '
    -0.42
     worship
    -0.40
    cho
    -0.38
     loving
    -0.37
    ’
    -0.37
    GeneratedCode
    -0.37
    ‘
    -0.36
     gave
    -0.35
     skick
    -0.34
    POSITIVE LOGITS
    CodedInputStream
    0.88
    StructEnd
    0.88
    sizeCache
    0.86
    клопе
    0.83
    EndGlobalSection
    0.82
    Personensuche
    0.82
     OMITBAD
    0.77
     Numerade
    0.75
    
    0.74
    Enllaces
    0.73
    Activations Density 0.001%

    No Known Activations