© 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. 72943
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    WithIOException
    -0.63
     AssemblyCulture
    -0.62
     nahilalakip
    -0.59
    queryInterface
    -0.59
    rizona
    -0.58
    存于互联网档案馆
    -0.55
     AssemblyProduct
    -0.54
    __":
    -0.54
    verwijspagina
    -0.54
    <%=
    -0.53
    POSITIVE LOGITS
    bcryptjs
    0.49
    uxxxx
    0.48
    AW
    0.47
     LW
    0.45
    STR
    0.44
    Competi
    0.44
    ational
    0.44
     Brou
    0.43
     munic
    0.43
    becker
    0.43
    Activations Density 0.000%

    No Known Activations