© 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. 75613
    Prev
    Next
    INDEX
    Explanations

    code or data snippets

    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
    ">//
    -0.60
     HasFactory
    -0.58
    SourceChecksum
    -0.56
    ConstraintMaker
    -0.56
    BufferException
    -0.56
    LayoutPanel
    -0.54
    lid
    -0.54
     okuyayım
    -0.54
    abstractmethod
    -0.54
     Pans
    -0.52
    POSITIVE LOGITS
    insics
    0.47
    học
    0.45
     թվական
    0.45
     millón
    0.45
    isseaux
    0.44
    uvo
    0.44
    ώς
    0.43
    mbang
    0.43
    +:+
    0.43
    navigate
    0.42
    Activations Density 0.001%

    No Known Activations