© 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. 5-CLT-HP
    7. 5915
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     sauvages
    -0.60
     fraî
    -0.59
     réguli
    -0.59
     démocr
    -0.59
     fumée
    -0.58
     espirituales
    -0.57
     riduzione
    -0.56
     déploy
    -0.56
     femeninos
    -0.54
     élevées
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
    enterOuterAlt
    0.60
    IndentedString
    0.60
     Signalez
    0.59
     createContext
    0.59
    VideoCapture
    0.58
    __(/*!
    0.58
    internalType
    0.57
    ELINE
    0.57
     Line
    0.56
    Activations Density 0.001%

    No Known Activations