© 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. 38871
    Prev
    Next
    INDEX
    Explanations

    able

    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
     ability
    -1.52
     able
    -1.34
     Ability
    -1.23
    Ability
    -1.12
    ability
    -1.09
     Able
    -1.00
    Able
    -0.97
     abilities
    -0.86
     Fähigkeit
    -0.86
     capaces
    -0.85
    POSITIVE LOGITS
     to
    1.33
    to
    0.55
     defended
    0.48
     keep
    0.47
     incomplète
    0.47
     negotiated
    0.46
     mobilize
    0.46
    e
    0.45
     performed
    0.45
     identified
    0.44
    Activations Density 0.041%

    No Known Activations