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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1856
    Prev
    Next
    INDEX
    Explanations

    movement, minute

    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
     ſeveral
    -0.88
     myſelf
    -0.84
     houſe
    -0.83
    WebVitals
    -0.82
     leſs
    -0.82
     doubtnut
    -0.80
     ſtate
    -0.80
     Jefus
    -0.79
     fubject
    -0.78
     Anſ
    -0.75
    POSITIVE LOGITS
    ,
    0.54
     of
    0.53
    dymyr
    0.52
     to
    0.50
    .
    0.50
     if
    0.49
    p
    0.47
    al
    0.47
     so
    0.46
    hold
    0.46
    Activations Density 0.047%

    No Known Activations