© 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. 4-CLT-HP
    7. 269
    Prev
    Next
    INDEX
    Explanations

    of

    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
    畿
    -0.47
    patron
    -0.44
    PerSecond
    -0.43
     campagne
    -0.43
     campagna
    -0.42
     Besar
    -0.42
     campaigns
    -0.41
    Mvh
    -0.40
     سكانية
    -0.40
    Референце
    -0.40
    POSITIVE LOGITS
     action
    1.04
    UnusedPrivate
    0.84
    action
    0.82
    Action
    0.80
     Action
    0.80
    webElementXpaths
    0.78
    BeginContext
    0.69
    saraba
    0.68
     ACTION
    0.68
    kloped
    0.66
    Activations Density 0.011%

    No Known Activations