© 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. 1-RES-MATRYOSHKA-DC
    7. 338
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving ratios or fractions

    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
    PreferredItem
    -0.75
    migrationBuilder
    -0.73
    SerializedSize
    -0.68
    ClientSize
    -0.63
    NewGuid
    -0.60
    jande
    -0.59
    msgTypes
    -0.58
    OrNil
    -0.56
     oprot
    -0.55
     الحره
    -0.54
    POSITIVE LOGITS
    frac
    4.13
    dfrac
    3.14
    mfrac
    2.84
     frac
    2.58
    tfrac
    2.30
    Frac
    1.47
    fraction
    1.39
     fractions
    1.37
     fraction
    1.30
    fract
    1.30
    Activations Density 0.614%

    No Known Activations