© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94777
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     AssemblyCulture
    -0.72
    findpost
    -0.69
    TagHelper
    -0.69
    FieldError
    -0.66
     AppColors
    -0.64
    OGND
    -0.64
    fromnode
    -0.64
    Hauptartikel
    -0.62
    DeleteMapping
    -0.62
    GOTREF
    -0.62
    POSITIVE LOGITS
    ,
    0.49
     fact
    0.44
    sciences
    0.43
    UBL
    0.43
    simum
    0.43
    similarity
    0.42
    NEA
    0.42
     Tinggi
    0.42
    pure
    0.40
     sû
    0.40
    Activations Density 0.005%

    No Known Activations