© 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. 77650
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
     interval
    -0.58
     Interval
    -0.57
    PhysRevLett
    -0.56
     HomeComponent
    -0.50
     visitor
    -0.50
    外部链接
    -0.49
    bronn
    -0.49
     Alamy
    -0.49
     Blan
    -0.48
    Interval
    -0.48
    POSITIVE LOGITS
     resourceCulture
    0.55
     Ause
    0.50
    ysty
    0.49
    ɵɵ
    0.48
     المعيارى
    0.48
    tagHelperRunner
    0.46
     initComponents
    0.46
    omiast
    0.45
    PTS
    0.45
    ntax
    0.45
    Activations Density 0.000%

    No Known Activations