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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3172
    Prev
    Next
    INDEX
    Explanations

    submitted

    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
    setVerticalGroup
    -0.63
    LikeLiked
    -0.59
    ).”
    -0.54
    UrlResolution
    -0.52
    municipi
    -0.49
    iltà
    -0.48
    ),”
    -0.47
    ).—
    -0.47
     Iggy
    -0.46
     laikā
    -0.46
    POSITIVE LOGITS
    __(/*!
    0.63
    ViewFeatures
    0.61
    MemoryWarning
    0.61
     समीक्षाओं
    0.57
    Personensuche
    0.56
     nakalista
    0.54
    toral
    0.54
    +#+
    0.54
    SequentialGroup
    0.53
    Parcelable
    0.50
    Activations Density 0.320%

    No Known Activations