© 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. 5-CLT-HP
    7. 3731
    Prev
    Next
    INDEX
    Explanations

    returning best guess based on failure to find other pattern:, utils

    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
     unknownFields
    -0.79
    FailureListener
    -0.66
    ImageContext
    -0.63
    EDEFAULT
    -0.63
    tvguidetime
    -0.61
    beiro
    -0.61
    weif
    -0.58
    strates
    -0.57
    Gweler
    -0.57
    ьаж
    -0.57
    POSITIVE LOGITS
     CURLOPT
    0.63
     Corbu
    0.48
     sun
    0.47
     Sun
    0.46
     BoxDecoration
    0.45
    gypte
    0.43
    Sun
    0.42
     sinar
    0.41
     Argus
    0.41
    LEGGI
    0.40
    Activations Density 0.001%

    No Known Activations