© 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. 0-CLT-HP
    7. 42360
    Prev
    Next
    INDEX
    Explanations

    Names code legal cases

    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
    WriteTagHelper
    -0.58
     chaque
    -0.57
    +#+
    -0.56
     varje
    -0.56
    |}\
    -0.56
    Chaque
    -0.56
    UrlResolution
    -0.55
     StringTokenizer
    -0.55
    ंदीखरीदारी
    -0.54
     giản
    -0.52
    POSITIVE LOGITS
    IUrlHelper
    0.63
    汰
    0.56
    PARATUS
    0.56
     <=",
    0.56
    EndContext
    0.55
     оригіналу
    0.55
    resave
    0.52
    writeFieldEnd
    0.50
    Kariera
    0.50
    LookAnd
    0.49
    Activations Density 0.139%

    No Known Activations