© 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. 5-CLT-HP
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    manded

    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
     mehrfach
    -0.69
     repeatedly
    -0.65
     fréquemment
    -0.64
     régulièrement
    -0.62
     regelmatig
    -0.61
    多次
    -0.61
     constantemente
    -0.60
     mehrm
    -0.60
     frequently
    -0.60
     Repeated
    -0.60
    POSITIVE LOGITS
    EndInit
    0.64
    mybatisplus
    0.63
     defaultstate
    0.60
    큼
    0.60
    tagHelperRunner
    0.59
    webElementXpaths
    0.57
    Vezi
    0.54
     تانيه
    0.53
     सत्यापित
    0.52
     lenker
    0.52
    Activations Density 0.034%

    No Known Activations