© 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. 0-CLT-HP
    7. 97610
    Prev
    Next
    INDEX
    Explanations

    references/arguments

    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
     Fig
    -0.53
    VersionUID
    -0.53
     cellpadding
    -0.46
     ―――――
    -0.46
    }%
    -0.45
     FIG
    -0.44
     ویکی‌پدیای
    -0.44
     ་་
    -0.44
    tvguidetime
    -0.44
    ’”
    -0.44
    POSITIVE LOGITS
    WriteTagHelper
    0.61
     Against
    0.57
    s
    0.56
    exprimer
    0.56
     publicitaires
    0.55
     propOrder
    0.55
    S
    0.55
     télécharge
    0.54
     détru
    0.54
     genoux
    0.54
    Activations Density 1.549%

    No Known Activations