© 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. 0-RES-MATRYOSHKA-DC
    7. 15196
    Prev
    Next
    INDEX
    Explanations

    numerical or coded identifiers in data

    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
     ax
    -1.23
     axe
    -1.23
     Axe
    -1.02
     Ax
    -0.99
     axes
    -0.83
    CodeAttribute
    -0.81
     Axes
    -0.77
    Axe
    -0.74
    Ax
    -0.72
     axial
    -0.67
    POSITIVE LOGITS
    ax
    1.84
     cuivre
    0.69
     ordinaire
    0.65
     sottile
    0.60
     ordinaires
    0.59
     marinho
    0.58
     secondaire
    0.56
     stră
    0.56
     Lilith
    0.56
     Butte
    0.55
    Activations Density 0.002%

    No Known Activations