© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93524
    Prev
    Next
    INDEX
    Explanations

    acronyms/abbreviations

    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
    ids
    -1.25
    IDS
    -1.16
     ids
    -0.83
    IDs
    -0.76
     IDS
    -0.74
    iba
    -0.73
    protoc
    -0.70
    Ids
    -0.66
    unknownFields
    -0.60
    iented
    -0.59
    POSITIVE LOGITS
    webElementXpaths
    0.62
    yntaxException
    0.51
     EconPapers
    0.50
    UseVisualStyle
    0.48
    InOut
    0.48
    rivial
    0.47
    ymce
    0.45
     voluntarios
    0.44
     mécanisme
    0.44
    cipar
    0.43
    Activations Density 0.211%

    No Known Activations