© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46136
    Prev
    Next
    INDEX
    Explanations

    ogonal

    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
    ogonal
    -2.33
    timedia
    -1.15
    MLLoader
    -0.60
    TintMode
    -0.51
    MERCIAL
    -0.49
     uncin
    -0.48
    selaer
    -0.48
     Его
    -0.47
    odziel
    -0.45
    pital
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.61
     AssemblyCulture
    0.58
    InitVars
    0.56
    OGND
    0.53
    awtextra
    0.52
    الحياه
    0.51
     trône
    0.50
    âne
    0.50
     vectorielle
    0.49
    toor
    0.49
    Activations Density 0.013%

    No Known Activations