© 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. 95104
    Prev
    Next
    INDEX
    Explanations

    Intersection

    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
     intersections
    -0.73
    StructEnd
    -0.70
     betweenstory
    -0.67
     intersection
    -0.65
     виправивши
    -0.64
    cèse
    -0.63
     ་་
    -0.62
     Whigs
    -0.62
     Theſe
    -0.61
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
    jsonwebtoken
    0.61
    BASEPATH
    0.52
     shut
    0.50
     it
    0.50
     “
    0.49
     OnInit
    0.49
    stdc
    0.49
     plotly
    0.47
    InstanceState
    0.46
     referenties
    0.46
    Activations Density 0.175%

    No Known Activations