© 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. 20-CLT-HP
    7. 77524
    Prev
    Next
    INDEX
    Explanations

    Technical passages

    np_max-act-logits · 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
     CreateTagHelper
    -0.53
    Général
    -0.52
    Зноскі
    -0.52
    posia
    -0.50
     ivelany
    -0.50
    ABULARY
    -0.49
    #
    -0.48
     glatt
    -0.48
    __":
    -0.47
    INCREF
    -0.47
    POSITIVE LOGITS
    prepareStatement
    0.49
    Geplaatst
    0.46
    getItemId
    0.44
    DialogContent
    0.43
    webElement
    0.43
     fec
    0.43
     armon
    0.42
     Samuels
    0.42
    wpi
    0.42
    istic
    0.42
    Activations Density 0.007%

    No Known Activations