© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1705
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    findpost
    -0.60
    Portale
    -0.57
    تقاوى
    -0.56
    -£
    -0.56
     समीक्षाओं
    -0.54
     Reverso
    -0.53
     كومونز
    -0.49
     zweier
    -0.49
     twenty
    -0.47
    Nazionale
    -0.47
    POSITIVE LOGITS
    ']?>
    0.62
    AccessFile
    0.60
     Marin
    0.57
     Dul
    0.57
     Sut
    0.56
     Dyke
    0.56
     Catch
    0.55
     Desire
    0.55
     Crane
    0.54
     Solano
    0.53
    Activations Density 0.032%

    No Known Activations