© 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. 5-CLT-HP
    7. 98083
    Prev
    Next
    INDEX
    Explanations

    Connecting words and punctuation

    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
     mergeFrom
    -0.55
     يتيمه
    -0.54
    Personensuche
    -0.50
     tartalomajánló
    -0.49
    enumi
    -0.49
    ConstraintMaker
    -0.49
    parsedMessage
    -0.49
    \
    -0.48
    +#+#
    -0.48
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
     Pas
    0.56
     <<<<<<<<<<<<<<
    0.55
    脚注の使い方
    0.54
     Falla
    0.52
     AssemblyCulture
    0.52
    Bibliograf
    0.50
     Traits
    0.49
    참고
    0.49
    amientos
    0.48
     veze
    0.48
    Activations Density 0.001%

    No Known Activations