© 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. 45802
    Prev
    Next
    INDEX
    Explanations

    achievement awards

    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
    gouv
    -0.51
    Decided
    -0.49
    retor
    -0.48
    tschaft
    -0.48
    htu
    -0.48
    cestershire
    -0.47
    istor
    -0.46
     et
    -0.46
    transQ
    -0.45
     copie
    -0.45
    POSITIVE LOGITS
    QApplication
    0.59
     bint
    0.58
     dynasties
    0.58
    createClass
    0.57
    -
    0.57
     Babylonian
    0.56
     Comprometido
    0.54
    endcsname
    0.54
    MarshalTo
    0.54
     Neop
    0.54
    Activations Density 0.481%

    No Known Activations