© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15248
    Prev
    Next
    INDEX
    Explanations

    references to external computational or programming concepts, such as code, scripts, or specific technical terms

    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
    +#+#
    -0.69
    thâu
    -0.68
    jfree
    -0.64
     Chwiliwch
    -0.62
    OGND
    -0.61
    +:+
    -0.60
    vaadin
    -0.59
    MSc
    -0.56
     GoogleFonts
    -0.56
    getMenuInflater
    -0.56
    POSITIVE LOGITS
    fclose
    0.67
    opress
    0.65
    wink
    0.65
    rigan
    0.62
    ruptcy
    0.60
    ICA
    0.59
    ered
    0.56
    getColumnIndex
    0.56
     apprehend
    0.55
     Lamar
    0.55
    Activations Density 0.074%

    No Known Activations