© 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. 97630
    Prev
    Next
    INDEX
    Explanations

    toma

    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
    ura
    -1.09
    asa
    -0.75
     ModelExpression
    -0.69
    tomas
    -0.67
    URA
    -0.67
    toma
    -0.66
     Pou
    -0.65
     à
    -0.64
     Berger
    -0.63
    ao
    -0.61
    POSITIVE LOGITS
     ervan
    0.55
    ReusableCell
    0.54
     auroit
    0.53
    :✨
    0.52
    Sucesor
    0.52
     Efq
    0.50
     étoit
    0.50
    ientôt
    0.49
    eterangan
    0.49
     avoient
    0.49
    Activations Density 0.030%

    No Known Activations