© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4564
    Prev
    Next
    INDEX
    Explanations

    lo

    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
    thâu
    -0.64
    )");
    -0.61
     Huguen
    -0.57
    %");
    -0.56
     pears
    -0.56
     fluor
    -0.52
     monogram
    -0.51
     Fez
    -0.50
     shoulder
    -0.49
     taxonomy
    -0.49
    POSITIVE LOGITS
     otomatig
    0.50
    Witam
    0.50
    WriteBarrier
    0.49
    #
    0.48
    Välislingid
    0.47
     financières
    0.47
    pulumi
    0.46
    BindingResult
    0.46
    steps
    0.46
     énergé
    0.46
    Activations Density 0.001%

    No Known Activations