© 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. 4561
    Prev
    Next
    INDEX
    Explanations

    research

    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
    rungsseite
    -0.83
    antaranya
    -0.71
    himself
    -0.66
     venons
    -0.65
     antaranya
    -0.63
     mismo
    -0.63
     lui
    -0.61
     preuves
    -0.61
    Hochspringen
    -0.60
     rayures
    -0.60
    POSITIVE LOGITS
     themselves
    1.01
     their
    0.81
     they
    0.71
     that
    0.67
     careers
    0.65
     thier
    0.59
    themselves
    0.53
     lives
    0.51
    owią
    0.51
     Himo
    0.50
    Activations Density 0.002%

    No Known Activations