© 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. 1-CLT-HP
    7. 13003
    Prev
    Next
    INDEX
    Explanations

    da

    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
    DA
    -1.36
    da
    -1.34
    Da
    -0.81
     DA
    -0.80
    daw
    -0.65
     Da
    -0.65
     da
    -0.64
    das
    -0.57
    dai
    -0.55
    principalColumn
    -0.53
    POSITIVE LOGITS
     Hira
    0.53
    Географи
    0.52
     behind
    0.51
    ··
    0.51
     Heidelberg
    0.51
     Hurley
    0.50
    ządz
    0.50
    BuilderFactory
    0.49
     Fav
    0.49
    inely
    0.49
    Activations Density 0.045%

    No Known Activations