© 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. 1-CLT-HP
    7. 15637
    Prev
    Next
    INDEX
    Explanations

    behave

    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
    ⓘ
    -0.70
     humanas
    -0.62
     ffilmiau
    -0.59
    merksam
    -0.58
     umana
    -0.57
     portata
    -0.55
     Heel
    -0.53
     humana
    -0.53
     honte
    -0.53
     coscienza
    -0.52
    POSITIVE LOGITS
    
    0.62
    NSNotification
    0.53
    ftagPool
    0.51
     fac
    0.49
     GenerationType
    0.49
    apimachinery
    0.49
    jsonwebtoken
    0.47
     RSSSF
    0.47
    epis
    0.46
    __*/
    0.46
    Activations Density 0.072%

    No Known Activations