© 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. 1-CLT-HP
    7. 45648
    Prev
    Next
    INDEX
    Explanations

    eternity

    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
     Gaul
    -0.87
     eternity
    -0.85
    ValueStyle
    -0.76
     Eternity
    -0.70
    saraba
    -0.56
     Nico
    -0.50
    >[]
    -0.49
    "})
    -0.48
    Nico
    -0.46
    immel
    -0.45
    POSITIVE LOGITS
    SaveChangesAsync
    0.64
    ξω
    0.60
    Datuak
    0.58
    TintMode
    0.58
    findpost
    0.57
    lidean
    0.57
    orianCalendar
    0.56
    __":
    0.55
    orszá
    0.54
     Derfor
    0.51
    Activations Density 0.030%

    No Known Activations