© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    names, especially Asian

    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
    iterations
    -0.40
    VS
    -0.39
    TI
    -0.38
     yore
    -0.37
    TIS
    -0.37
     allAfrica
    -0.36
    VI
    -0.35
     ignited
    -0.34
     camar
    -0.34
    ny
    -0.34
    POSITIVE LOGITS
    styleType
    0.73
     незавершена
    0.71
    Portail
    0.71
    AndEndTag
    0.67
     autorytatywna
    0.66
     виправивши
    0.66
    Hentet
    0.66
    expandindo
    0.66
    RTEE
    0.65
    شهاد
    0.63
    Activations Density 0.002%

    No Known Activations