© 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. 10064
    Prev
    Next
    INDEX
    Explanations

    stored

    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
     Stored
    -0.68
    ToBounds
    -0.56
     []:
    -0.53
     Storage
    -0.53
    nance
    -0.53
    storage
    -0.52
    stored
    -0.51
     storage
    -0.51
    Storage
    -0.51
    numerusform
    -0.50
    POSITIVE LOGITS
     defaultstate
    0.80
     للمعارف
    0.77
    ModelAdmin
    0.73
    GEBURTSDATUM
    0.71
    TestingModule
    0.66
     pinulongan
    0.64
    kháu
    0.61
    ⓧ
    0.61
     ligiloj
    0.60
     تضيفلها
    0.59
    Activations Density 0.027%

    No Known Activations