© 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. 97416
    Prev
    Next
    INDEX
    Explanations

    hydroxyl, vo

    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
    vo
    -1.42
     vo
    -0.71
    ConstraintMaker
    -0.69
     الحره
    -0.69
     المعيارى
    -0.66
    VO
    -0.65
    Portale
    -0.65
    vov
    -0.65
    во
    -0.64
     Vo
    -0.63
    POSITIVE LOGITS
    genstein
    0.50
    s
    0.50
    twimg
    0.49
    titleMargin
    0.48
    řen
    0.48
    áció
    0.46
    ánto
    0.46
    ounted
    0.45
    sos
    0.45
    chuan
    0.45
    Activations Density 0.291%

    No Known Activations