© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43223
    Prev
    Next
    INDEX
    Explanations

    conflict and movement

    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
     '\\;'
    -1.05
    oa̍t
    -0.94
     estekak
    -0.92
    IntoConstraints
    -0.87
     <=",
    -0.84
    RenderAtEndOf
    -0.82
    WebVitals
    -0.81
     فريبيس
    -0.76
     NSCoder
    -0.71
    bootstrapcdn
    -0.71
    POSITIVE LOGITS
    er
    0.71
    ه
    0.67
    led
    0.66
    e
    0.66
    o
    0.63
    a
    0.56
    s
    0.54
     like
    0.53
     in
    0.52
    i
    0.50
    Activations Density 0.759%

    No Known Activations