© 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. 1-CLT-HP
    7. 11967
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    up
    -0.72
     complètes
    -0.57
    if
    -0.54
    Up
    -0.50
    sell
    -0.50
     âgées
    -0.49
    down
    -0.49
    set
    -0.49
     înainte
    -0.48
    out
    -0.47
    POSITIVE LOGITS
    ]--;
    0.75
     the
    0.73
     oneself
    0.73
    DockStyle
    0.73
    ParallelGroup
    0.72
    awtextra
    0.69
    OGND
    0.69
    mergeFrom
    0.68
    AnchorStyles
    0.67
    ]='\
    0.66
    Activations Density 0.095%

    No Known Activations