© 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. 5-CLT-HP
    7. 96020
    Prev
    Next
    INDEX
    Explanations

    findings and reports

    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
     myö
    -0.63
     ennen
    -0.54
     many
    -0.53
     plusieurs
    -0.53
     several
    -0.52
     before
    -0.52
    isContained
    -0.50
    Kapcsolódó
    -0.50
    lösen
    -0.49
     hours
    -0.49
    POSITIVE LOGITS
     fince
    0.68
     since
    0.66
     ſtate
    0.63
    RenderAtEndOf
    0.63
    since
    0.63
    EndContext
    0.62
    IndentedString
    0.59
    seit
    0.57
     venons
    0.57
     ſen
    0.56
    Activations Density 0.007%

    No Known Activations