© 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. 91010
    Prev
    Next
    INDEX
    Explanations

    people

    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
    eseorang
    -0.75
    makeText
    -0.74
    KommentareTeilen
    -0.72
    عبة
    -0.70
     lenker
    -0.66
    tersebut
    -0.65
     personality
    -0.64
    Autoritní
    -0.64
    quatre
    -0.64
    ListTile
    -0.63
    POSITIVE LOGITS
    ie
    0.60
    e
    0.59
    o
    0.54
    er
    0.54
    ale
    0.54
    ies
    0.52
    et
    0.52
    ChildIndex
    0.52
    a
    0.52
     vulgares
    0.51
    Activations Density 0.050%

    No Known Activations