© 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. 77255
    Prev
    Next
    INDEX
    Explanations

    most

    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
    principalTable
    -0.87
     största
    -0.62
    IPAC
    -0.61
     głó
    -0.58
    MigrationBuilder
    -0.57
     scolaires
    -0.56
    andExpect
    -0.56
     huvud
    -0.56
    Main
    -0.55
    OrBuilder
    -0.55
    POSITIVE LOGITS
    <bos>
    0.66
     no
    0.61
    AdapterView
    0.58
     significantly
    0.53
     sign
    0.50
    WriteAttribute
    0.49
     NO
    0.48
     im
    0.47
    
    0.47
     sin
    0.45
    Activations Density 0.001%

    No Known Activations