© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97657
    Prev
    Next
    INDEX
    Explanations

    are

    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
     are
    -1.70
    are
    -1.18
    Are
    -1.00
     Theſe
    -0.96
     itſelf
    -0.94
     estão
    -0.94
     Are
    -0.92
     feroit
    -0.90
     abbildung
    -0.87
     ainfi
    -0.86
    POSITIVE LOGITS
     a
    1.06
     not
    0.96
     able
    0.94
     an
    0.80
     the
    0.80
     considered
    0.73
     always
    0.71
     done
    0.71
     supposed
    0.71
     also
    0.70
    Activations Density 0.316%

    No Known Activations