© 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. 5-CLT-HP
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    隈
    -0.39
    ltä
    -0.38
     }));
    -0.36
    Okey
    -0.36
     الحره
    -0.36
    "]));
    -0.36
    <?
    -0.36
    tifies
    -0.35
     terecht
    -0.35
    untut
    -0.35
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.72
     himſelf
    0.67
    ArgsConstructor
    0.66
    kic
    0.61
     itſelf
    0.61
    AZINE
    0.60
     smtplib
    0.60
    PageModule
    0.60
    PRWEB
    0.59
     purpoſe
    0.59
    Activations Density 0.021%

    No Known Activations