© 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. 1-RES-MATRYOSHKA-DC
    7. 724
    Prev
    Next
    INDEX
    Explanations

    code snippets related to system calls and file operations

    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
    protoimpl
    -0.77
     Normdatei
    -0.70
     EconPapers
    -0.66
     numerus
    -0.64
    Diwedd
    -0.63
     Administrativna
    -0.63
    ThroughAttribute
    -0.63
    doir
    -0.62
    kasten
    -0.61
     Gabb
    -0.61
    POSITIVE LOGITS
     char
    4.31
    char
    3.88
    Char
    3.59
     Char
    3.55
    CHAR
    3.16
     CHAR
    3.05
     chars
    2.42
    chars
    2.19
    chara
    1.96
    Chars
    1.93
    Activations Density 0.039%

    No Known Activations