© 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. 0-CLT-HP
    7. 93932
    Prev
    Next
    INDEX
    Explanations

    something

    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
    ########.
    -0.73
    Something
    -0.68
     Something
    -0.64
     apparti
    -0.64
     puisse
    -0.64
     qualcosa
    -0.63
     condamné
    -0.62
     laquelle
    -0.62
     uintptr
    -0.62
     priorité
    -0.62
    POSITIVE LOGITS
    stateProvider
    0.63
     sequelize
    0.61
     big
    0.60
    brainly
    0.59
     other
    0.57
    jstor
    0.55
    став
    0.54
     your
    0.53
    resol
    0.52
     bigger
    0.51
    Activations Density 0.019%

    No Known Activations