© 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. 4-CLT-HP
    7. 4872
    Prev
    Next
    INDEX
    Explanations

    0

    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
     nahilalakip
    -0.69
     <=",
    -0.64
     AssemblyCulture
    -0.59
    SourceChecksum
    -0.59
    expandindo
    -0.57
     CWE
    -0.57
     sẻ
    -0.57
    KommentareTeilen
    -0.54
     Taktlose
    -0.53
     myſelf
    -0.53
    POSITIVE LOGITS
    WireFormat
    0.60
    </em>
    0.51
    7
    0.48
    tiko
    0.44
    CreateIndex
    0.44
    bazel
    0.43
     Baillargeon
    0.43
     Prins
    0.43
    GRID
    0.43
    })}\
    0.42
    Activations Density 0.004%

    No Known Activations