© 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. 1-CLT-HP
    7. 10894
    Prev
    Next
    INDEX
    Explanations

    strange odd weird

    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
    IVEREF
    -0.69
     Италијани
    -0.58
    chyma
    -0.58
    ValueStyle
    -0.58
    kheim
    -0.56
    Diamonds
    -0.54
    ArrowToggle
    -0.53
     Motos
    -0.52
    getResultList
    -0.52
    webElementXpaths
    -0.52
    POSITIVE LOGITS
     esternos
    0.63
    tonsoft
    0.61
    awtextra
    0.56
    AutoScaleMode
    0.49
    ulun
    0.48
    FontOfSize
    0.46
    MLLoader
    0.45
    ngths
    0.45
    BeginContext
    0.44
    szönöm
    0.44
    Activations Density 0.007%

    No Known Activations