© 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. 988
    Prev
    Next
    INDEX
    Explanations

    Ph

    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
    OGND
    -0.73
     Infórmanos
    -0.67
    ьаж
    -0.67
     InputDecoration
    -0.63
    횟
    -0.60
     Zayed
    -0.60
     Steal
    -0.58
     متعلقه
    -0.58
     مرئيه
    -0.57
    richTextPanel
    -0.56
    POSITIVE LOGITS
    isher
    0.68
    ish
    0.66
    ISH
    0.64
    ishing
    0.61
    ishy
    0.59
    ishes
    0.59
    ishable
    0.56
    ising
    0.56
    ModelBuilder
    0.53
    ishi
    0.52
    Activations Density 0.002%

    No Known Activations