© 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. 4-CLT-HP
    7. 66
    Prev
    Next
    INDEX
    Explanations

    offspring

    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
    paravant
    -0.47
    forward
    -0.46
    ate
    -0.45
    erover
    -0.44
    robat
    -0.44
    AndEndTag
    -0.42
    DotNetBar
    -0.42
    kete
    -0.41
    cules
    -0.41
    quad
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.77
    ########.
    0.56
    уда
    0.54
    ActionResult
    0.54
    ㎡
    0.53
     الحره
    0.52
    MENAFN
    0.52
     تانيه
    0.52
     NSCoder
    0.52
    parseColor
    0.50
    Activations Density 0.003%

    No Known Activations