© 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. 1-CLT-HP
    7. 10054
    Prev
    Next
    INDEX
    Explanations

    problem-solving contexts

    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
     Efq
    -1.02
    ^(@)
    -1.01
    principalColumn
    -1.00
    دانشنامهٔ
    -0.99
    migrationBuilder
    -0.99
     Roskov
    -0.98
     beginnetje
    -0.98
    +#+#
    -0.96
    ſelf
    -0.96
    ArgumentParser
    -0.95
    POSITIVE LOGITS
    .
    0.60
     &
    0.47
    ↵
    0.43
     \\
    0.39
    ...
    0.39
     ہیں۔
    0.37
      
    0.37
     }}">
    0.36
     I
    0.36
    ?
    0.36
    Activations Density 0.013%

    No Known Activations