© 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. 77467
    Prev
    Next
    INDEX
    Explanations

    technical computing topics

    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
    ⎨
    -0.63
     Roskov
    -0.63
     Bioaccumulative
    -0.61
    ftagPool
    -0.56
     ApiException
    -0.54
    Története
    -0.54
    ThroughAttribute
    -0.53
     Lauderdale
    -0.53
    ientôt
    -0.53
    reggio
    -0.53
    POSITIVE LOGITS
    StructEnd
    0.62
     society
    0.57
     Society
    0.55
     mystical
    0.52
    posedge
    0.50
     community
    0.49
     social
    0.49
     sociali
    0.47
     general
    0.47
     compact
    0.46
    Activations Density 0.000%

    No Known Activations