© 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. 4-CLT-HP
    7. 3374
    Prev
    Next
    INDEX
    Explanations

    is

    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
    Попис
    -0.92
    LookAnd
    -0.82
    MergeFrom
    -0.79
    ScopeManager
    -0.76
     nakalista
    -0.75
     kasarigan
    -0.74
    lapsingToolbar
    -0.73
    __':
    -0.73
    "],
    -0.72
    .*")]
    -0.71
    POSITIVE LOGITS
     to
    0.82
     for
    0.56
     esenciales
    0.53
     essenciais
    0.50
    part
    0.49
     clé
    0.49
     majeur
    0.48
    to
    0.48
    Part
    0.47
    critical
    0.47
    Activations Density 0.005%

    No Known Activations