© 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. 4-CLT-HP
    7. 4441
    Prev
    Next
    INDEX
    Explanations

    body

    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
    twimg
    -0.72
     pinulongan
    -0.69
     NUKAT
    -0.64
    atisk
    -0.63
    ativité
    -0.61
    الدراسه
    -0.59
     فريبيس
    -0.59
    olescence
    -0.59
     brothers
    -0.58
    esez
    -0.58
    POSITIVE LOGITS
     confronti
    0.46
     profonde
    0.42
    irent
    0.40
     csal
    0.40
    ort
    0.40
    rino
    0.40
    jenige
    0.40
    got
    0.39
    antin
    0.39
    reactivex
    0.38
    Activations Density 0.009%

    No Known Activations