© 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. 3397
    Prev
    Next
    INDEX
    Explanations

    both/neither

    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
    Personensuche
    -0.73
    extAlignment
    -0.58
    }}/>
    -0.57
     defStyle
    -0.56
    IntoConstraints
    -0.56
    StoryboardSegue
    -0.54
    showing
    -0.52
     nawr
    -0.51
    />";
    -0.51
    msgTypes
    -0.50
    POSITIVE LOGITS
     require
    0.75
    require
    0.63
     will
    0.61
     need
    0.60
     generally
    0.59
     may
    0.56
     receive
    0.56
     can
    0.56
     have
    0.55
     should
    0.54
    Activations Density 0.004%

    No Known Activations