© 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. 3441
    Prev
    Next
    INDEX
    Explanations

    time

    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
     beginnetje
    -0.81
    <bos>
    -0.75
    LookAnd
    -0.71
    twimg
    -0.67
    Portale
    -0.66
     الدولى
    -0.64
    InjectAttribute
    -0.61
    WebServlet
    -0.60
    تقاوى
    -0.60
    UnknownFields
    -0.59
    POSITIVE LOGITS
    ichel
    0.56
     leaving
    0.52
     leave
    0.51
    teros
    0.51
    webElement
    0.49
    mola
    0.49
    leave
    0.48
     Antonius
    0.48
    leaving
    0.47
    #+#
    0.47
    Activations Density 0.004%

    No Known Activations