© 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. 97500
    Prev
    Next
    INDEX
    Explanations

    Andrews

    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
    achio
    -0.94
    ArgsConstructor
    -0.75
    ManagedBean
    -0.75
    ChromeDriver
    -0.74
     BIBSYS
    -0.73
    ontology
    -0.72
     angefü
    -0.72
    ]")]
    -0.71
    jspx
    -0.71
    INSEE
    -0.70
    POSITIVE LOGITS
    ness
    0.66
    ity
    0.52
    CrossRef
    0.48
    ment
    0.47
    Према
    0.47
    ITY
    0.47
    AMENTE
    0.45
     
    0.44
     “
    0.44
    NESS
    0.43
    Activations Density 0.107%

    No Known Activations