© 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. 43265
    Prev
    Next
    INDEX
    Explanations

    cept

    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
    ole
    -0.90
    cept
    -0.85
     sanitaires
    -0.71
    ounced
    -0.63
     indipendente
    -0.62
    nom
    -0.59
     safeguarding
    -0.59
     وتسجيلات
    -0.59
    glEnd
    -0.55
     dépasse
    -0.55
    POSITIVE LOGITS
    PickerController
    0.58
    optionalTypeArgs
    0.57
    帖最后由
    0.56
     CreateTagHelper
    0.54
    parseDouble
    0.53
    ChildScrollView
    0.53
    ]$}
    0.52
    存于互联网档案馆
    0.51
    ValueGeneration
    0.51
    Acerca
    0.50
    Activations Density 0.461%

    No Known Activations