© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91106
    Prev
    Next
    INDEX
    Explanations

    persever

    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
    Negative Logits
     CURIAM
    -0.61
    RuleContext
    -0.60
    ponses
    -0.59
     themſelves
    -0.58
    ruptedException
    -0.58
     himſelf
    -0.57
     HMM
    -0.56
     myſelf
    -0.56
     tph
    -0.56
     poffe
    -0.54
    POSITIVE LOGITS
    ation
    0.72
    ing
    0.65
    ed
    0.64
     مرئيه
    0.64
    ations
    0.60
    ING
    0.57
    EndContext
    0.57
    homonymie
    0.56
    ant
    0.56
    ative
    0.55
    Activations Density 0.014%

    No Known Activations