© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72863
    Prev
    Next
    INDEX
    Explanations

    Software licenses and HTML headers

    np_max-act-logits · 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
     pouvoit
    -0.84
     rempliss
    -0.82
     feroit
    -0.82
     auroit
    -0.80
     figliu
    -0.78
     avoient
    -0.77
     rendent
    -0.77
    országban
    -0.76
     cappello
    -0.74
     Commencez
    -0.73
    POSITIVE LOGITS
    帖最后由
    0.36
    
    0.32
    endphp
    0.29
    }\]
    0.28
    hdashline
    0.27
    ")){
    
    0.26
    ousand
    0.26
    ")]
    
    0.25
    IsUnicode
    0.25
    ")));
    
    0.25
    Activations Density 0.002%

    No Known Activations