© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 975
    Prev
    Next
    INDEX
    Explanations

    the letter "A" followed by various other characters, often in what appears to be code or technical documentation

    oai_token-act-pair · gemini-2.0-flash
    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
     createSlice
    -0.74
    Autoritní
    -0.73
    LikeLiked
    -0.66
    CompilerServices
    -0.66
    TargetException
    -0.66
    ölkerung
    -0.65
    UnsafeEnabled
    -0.65
    الحياه
    -0.64
    noons
    -0.64
    ApiException
    -0.64
    POSITIVE LOGITS
    A
    1.99
     A
    1.74
    getA
    1.23
    Ａ
    1.07
    a
    1.00
    А
    0.92
     А
    0.89
    tA
    0.87
    iA
    0.85
    nA
    0.82
    Activations Density 0.781%

    No Known Activations