© 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. 4956
    Prev
    Next
    INDEX
    Explanations

    training

    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
    Tikang
    -0.59
     дописавши
    -0.58
    HasAnnotation
    -0.55
     Chwiliwch
    -0.54
    transQ
    -0.53
    rungsseite
    -0.52
     cardíaca
    -0.51
    oredCriteria
    -0.51
     disambiguazione
    -0.50
    Personensuche
    -0.49
    POSITIVE LOGITS
     for
    0.65
    utilisons
    0.63
     ev
    0.63
     capturing
    0.58
     evacu
    0.56
    헌
    0.50
     events
    0.48
     thiết
    0.48
    Extractor
    0.47
     tourisme
    0.47
    Activations Density 0.001%

    No Known Activations