© 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. 0-CLT-HP
    7. 95204
    Prev
    Next
    INDEX
    Explanations

    possibilities/evaluations

    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
     kaynağından
    -0.76
    JspWriter
    -0.76
     vPvB
    -0.75
     BorderRadius
    -0.66
    DeleteBehavior
    -0.66
     للمعارف
    -0.65
     ostavi
    -0.65
     HasFactory
    -0.65
     tartalomajánló
    -0.65
    Erstellt
    -0.63
    POSITIVE LOGITS
     onData
    0.48
    ])));
    0.47
    Suara
    0.47
    dolu
    0.46
    zerű
    0.45
    onaceous
    0.44
    ässe
    0.44
    scha
    0.42
     urea
    0.42
     chances
    0.42
    Activations Density 0.257%

    No Known Activations