© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43321
    Prev
    Next
    INDEX
    Explanations

    Non-specific broad nouns

    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
    asn
    -0.46
    arta
    -0.44
    epen
    -0.44
     Pri
    -0.44
     Art
    -0.43
    sies
    -0.43
    simon
    -0.43
    jsonPath
    -0.42
     que
    -0.42
    kins
    -0.42
    POSITIVE LOGITS
    etheless
    0.83
     تانيه
    0.68
     Приступљено
    0.66
    theless
    0.66
     Efq
    0.66
    σθαι
    0.64
    قایناق‌لار
    0.64
     doubtnut
    0.63
    <bos>
    0.62
    rrggbb
    0.61
    Activations Density 0.123%

    No Known Activations