© 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. 0-RES-MATRYOSHKA-DC
    7. 15635
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific function call pattern

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.91
    ########.
    -0.83
    enderror
    -0.74
    abstractmethod
    -0.66
    arakhand
    -0.65
    writeFieldEnd
    -0.65
     popoli
    -0.65
     GenerationType
    -0.64
    endforeach
    -0.64
    UnusedPrivate
    -0.63
    POSITIVE LOGITS
    Call
    1.95
     Call
    1.73
    CALL
    0.92
     CALL
    0.77
    Cal
    0.56
     Händ
    0.54
     Cal
    0.50
     Contact
    0.50
    OrNil
    0.46
    Stranger
    0.45
    Activations Density 0.002%

    No Known Activations