© 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. 98055
    Prev
    Next
    INDEX
    Explanations

    Filler words

    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
     BorderSide
    -0.51
     respectively
    -0.51
    liferay
    -0.50
    etc
    -0.48
     etc
    -0.48
    respectively
    -0.47
    Portale
    -0.47
    بوابة
    -0.46
    ViewFeatures
    -0.46
    KommentareTeilen
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.84
    ImageContext
    0.63
    vägen
    0.59
    XtraGrid
    0.59
     énergé
    0.57
     avoient
    0.57
     $_"
    0.57
    السكان
    0.56
     fidé
    0.56
    unknownFields
    0.55
    Activations Density 0.012%

    No Known Activations