© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2207
    Prev
    Next
    INDEX
    Explanations

    duration

    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
    цездатний
    -0.88
    setVerticalGroup
    -0.83
    MigrationBuilder
    -0.82
     AssemblyCulture
    -0.82
     فريبيس
    -0.81
     كومونز
    -0.80
    ########.
    -0.76
    IBarButtonItem
    -0.74
     препратки
    -0.73
     tartalomajánló
    -0.73
    POSITIVE LOGITS
     processed
    0.42
     Chao
    0.42
    воря
    0.42
     eredeti
    0.41
    SocketAddress
    0.41
     extra
    0.40
    ant
    0.40
    op
    0.40
     special
    0.39
     original
    0.39
    Activations Density 0.002%

    No Known Activations