© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97336
    Prev
    Next
    INDEX
    Explanations

    regression

    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
    RegressionTest
    -0.70
    tanleria
    -0.66
    EndTag
    -0.64
    InitVars
    -0.63
     "..\..\
    -0.63
     كومونز
    -0.61
     дописавши
    -0.59
    Satisfied
    -0.58
    ItemBackground
    -0.57
     fossero
    -0.57
    POSITIVE LOGITS
    chism
    0.50
    Lähteet
    0.48
     to
    0.46
     חיצוניים
    0.45
    ModelState
    0.44
    eding
    0.43
     الحره
    0.42
    afficheront
    0.41
     Zacks
    0.41
    Activité
    0.41
    Activations Density 0.003%

    No Known Activations