© 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. 20-CLT-HP
    7. 72570
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    was
    -0.49
     Republic
    -0.42
    holds
    -0.41
    mulos
    -0.37
     Was
    -0.36
    stdc
    -0.36
    Was
    -0.36
    ínu
    -0.35
     holds
    -0.35
    pc
    -0.34
    POSITIVE LOGITS
    ArrowToggle
    0.84
    aarrggbb
    0.76
     HasFactory
    0.74
     BoxDecoration
    0.73
    StoryboardSegue
    0.72
     chré
    0.71
    ⓧ
    0.70
    AccessorTable
    0.69
     kasarigan
    0.66
    reportWebVitals
    0.66
    Activations Density 0.000%

    No Known Activations