© 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. 3-RES-MATRYOSHKA-DC
    7. 2065
    Prev
    Next
    INDEX
    Explanations

    the character 'R' followed by other characters, likely related to code or identifiers

    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
    br
    -0.65
     Ir
    -0.60
    tr
    -0.57
    Marshaller
    -0.56
    Ir
    -0.55
     Brut
    -0.54
    spyOn
    -0.54
     pr
    -0.53
    cr
    -0.52
     Br
    -0.52
    POSITIVE LOGITS
    R
    1.73
     R
    1.70
    getR
    1.20
    Ｒ
    1.02
    enderror
    0.84
    𝑅
    0.82
    mR
    0.80
    aR
    0.75
    RPD
    0.74
    fR
    0.73
    Activations Density 0.341%

    No Known Activations