© 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. 40022
    Prev
    Next
    INDEX
    Explanations

    can

    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
     can
    -0.60
     are
    -0.60
     is
    -0.59
    can
    -0.57
     Last
    -0.56
     occurred
    -0.56
     resulted
    -0.55
     Cause
    -0.54
     CAUSE
    -0.54
    last
    -0.53
    POSITIVE LOGITS
     ſind
    0.93
     myſelf
    0.93
     uſe
    0.88
    ^(@)
    0.82
     ſtate
    0.79
     obſ
    0.76
    ükemmel
    0.75
    UnusedPrivate
    0.75
     himſelf
    0.74
    createCanvas
    0.74
    Activations Density 0.035%

    No Known Activations