© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97661
    Prev
    Next
    INDEX
    Explanations

    OSA

    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
    ation
    -0.82
    ate
    -0.79
    SPATH
    -0.64
    ATE
    -0.63
    anken
    -0.60
    ATION
    -0.58
     transf
    -0.56
     denti
    -0.54
     kre
    -0.54
    SPE
    -0.54
    POSITIVE LOGITS
     mérite
    0.66
     descrizione
    0.64
     hanem
    0.63
    zaamheid
    0.62
     pauvreté
    0.61
     valutazione
    0.60
     presentazione
    0.60
    曖昧さ回避
    0.59
     scolaires
    0.59
    Ҭ
    0.59
    Activations Density 0.017%

    No Known Activations