© 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. 45199
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ंदीखरीदारी
    -0.84
    ########.
    -0.82
     AssemblyCulture
    -0.79
    hyrchwyd
    -0.79
     lenker
    -0.73
    parsedMessage
    -0.73
    OGND
    -0.73
    出版年
    -0.69
    脚注の使い方
    -0.66
     ब्रेकडाउन
    -0.65
    POSITIVE LOGITS
     reich
    0.54
     logra
    0.46
    ]))
    0.46
     delan
    0.43
    0.43
    getActiveSheet
    0.42
     предлагает
    0.41
    Drei
    0.41
    UniformLocation
    0.41
     successo
    0.41
    Activations Density 0.229%
    No Known Activations