© 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. 6159
    Prev
    Next
    INDEX
    Explanations

    video games

    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
     enhancement
    -0.57
     Enhancement
    -0.57
    Data
    -0.46
    Enhance
    -0.45
     ar
    -0.44
    Біографія
    -0.43
    Handlung
    -0.42
    物
    -0.42
     Data
    -0.42
    menschen
    -0.42
    POSITIVE LOGITS
    antMatchers
    0.81
     فريبيس
    0.79
    mergeFrom
    0.69
    AndEndTag
    0.66
    IVEREF
    0.65
    zzleHttp
    0.65
    RetentionPolicy
    0.64
     Normdatei
    0.62
    RectangleBorder
    0.60
     BrowserModule
    0.60
    Activations Density 0.007%

    No Known Activations