© 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. 97689
    Prev
    Next
    INDEX
    Explanations

    Causes / affected

    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
     causes
    -1.52
     Causes
    -1.41
    Causes
    -1.41
    causes
    -1.41
     Ursachen
    -0.95
     affected
    -0.92
     causas
    -0.90
     Affected
    -0.86
    affected
    -0.84
    cause
    -0.83
    POSITIVE LOGITS
    awtextra
    0.75
    #+#
    0.63
    unnitel
    0.62
    jątk
    0.54
     Staaten
    0.52
    phazard
    0.50
     rush
    0.50
     Riesen
    0.49
    umbag
    0.49
     paljon
    0.49
    Activations Density 0.034%

    No Known Activations