© 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. 1-CLT-HP
    7. 10352
    Prev
    Next
    INDEX
    Explanations

    MPa

    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
    geber
    -0.46
    hind
    -0.43
    ully
    -0.43
    unlocked
    -0.42
    webElementXpaths
    -0.42
     Hansen
    -0.40
    Publicado
    -0.40
    nair
    -0.40
     rela
    -0.39
     sembl
    -0.39
    POSITIVE LOGITS
    EndContext
    0.71
    RectangleBorder
    0.70
     OMR
    0.69
     Baillargeon
    0.66
    oporosis
    0.65
     ControllerBase
    0.65
     insuffisamment
    0.64
     المعيارى
    0.63
    AnchorStyles
    0.62
     onOptions
    0.62
    Activations Density 0.005%

    No Known Activations