© 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. 2-RES-MATRYOSHKA-DC
    7. 3254
    Prev
    Next
    INDEX
    Explanations

    expressions involving the variable 'a' with high numeric values

    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
     A
    -1.45
    A
    -1.18
     А
    -0.77
     An
    -0.76
    nA
    -0.73
    tA
    -0.71
    An
    -0.68
    rA
    -0.66
    География
    -0.63
    Ａ
    -0.62
    POSITIVE LOGITS
    a
    1.42
    aR
    0.93
    expandindo
    0.74
    aI
    0.73
    
    0.69
    Datuak
    0.68
    aac
    0.64
    aed
    0.64
    aS
    0.63
     שוליים
    0.62
    Activations Density 0.218%

    No Known Activations