© 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. 0-CLT-HP
    7. 38827
    Prev
    Next
    INDEX
    Explanations

    source

    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
     source
    -1.12
    source
    -1.09
     Source
    -0.96
     sources
    -0.94
    Source
    -0.87
     SOURCE
    -0.85
     Sources
    -0.84
    sources
    -0.83
     fuente
    -0.79
    源
    -0.79
    POSITIVE LOGITS
    __((
    0.71
    PerformLayout
    0.68
     consulate
    0.66
     Europeo
    0.63
     Ayuntamiento
    0.62
     IndexPath
    0.61
    נגלית
    0.60
     Nicosia
    0.60
    XMLSchema
    0.59
    UrlResolution
    0.58
    Activations Density 0.030%

    No Known Activations