© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13960
    Prev
    Next
    INDEX
    Explanations

    recognition of specific control signals or command patterns related to enabling or disabling features

    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
    fc
    -1.11
    ThroughAttribute
    -0.79
     fc
    -0.75
     ISNI
    -0.66
     DRM
    -0.59
     Hohen
    -0.58
     Hentet
    -0.57
     Popper
    -0.56
     nô
    -0.55
     rehearsals
    -0.55
    POSITIVE LOGITS
    FC
    1.48
    Diwedd
    0.57
     @"/
    0.54
    Locke
    0.54
    __(/*!
    0.51
     cív
    0.49
    usermodel
    0.47
    ḷ
    0.47
    IndentedString
    0.47
     समीक्षाओं
    0.46
    Activations Density 0.002%

    No Known Activations