© 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. 38966
    Prev
    Next
    INDEX
    Explanations

    usage and references

    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
    GEBURTSDATUM
    -0.82
    UserScript
    -0.78
     препратки
    -0.77
    ंदीखरीदारी
    -0.76
    󠁢
    -0.71
    EDEFAULT
    -0.71
     lenker
    -0.69
     propTypes
    -0.67
    GTCX
    -0.66
     tartalomajánló
    -0.65
    POSITIVE LOGITS
    indo
    0.47
    thol
    0.46
    XtraReports
    0.45
    كون
    0.45
    ValueGeneration
    0.44
    ️
    0.43
    fat
    0.41
    — 
    0.40
    SPJ
    0.40
    HomeAsUp
    0.40
    Activations Density 0.240%

    No Known Activations