© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71873
    Prev
    Next
    INDEX
    Explanations

    Uncommon words

    np_max-act-logits · 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
     dozen
    -0.93
     hundred
    -0.85
     least
    -0.83
    ximately
    -0.77
     than
    -0.73
    dozen
    -0.69
    выше
    -0.66
     thousand
    -0.65
     fifty
    -0.65
     atleast
    -0.63
    POSITIVE LOGITS
     EconPapers
    0.57
    }.
    0.57
    ).
    0.56
    -->
    0.55
     հղումներ
    0.55
     jäsen
    0.55
    barui
    0.55
    lgari
    0.54
    GEBURTS
    0.54
    ".
    0.53
    Activations Density 0.001%

    No Known Activations