© 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. 45321
    Prev
    Next
    INDEX
    Explanations

    oblastoma

    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
     lined
    -0.76
     banning
    -0.71
     Lined
    -0.68
     Mandate
    -0.67
    SourceChecksum
    -0.63
     Bend
    -0.62
    sidemargin
    -0.61
     unfolds
    -0.60
     BEND
    -0.59
     listing
    -0.58
    POSITIVE LOGITS
    orothy
    0.53
    </thead>
    0.52
    SequentialGroup
    0.50
    <!--[
    0.48
    робнее
    0.48
    іга
    0.48
    ized
    0.47
    endphp
    0.46
    ned
    0.46
    addOn
    0.45
    Activations Density 1.360%

    No Known Activations