© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    patterns in dietary data that categorize individuals into distinct dietary groups

    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
    SourceChecksum
    -0.79
    AutoScaleMode
    -0.69
    ChromeDriver
    -0.68
    ImageField
    -0.66
    VersionUID
    -0.63
    fjspx
    -0.60
     оса
    -0.59
    WebServlet
    -0.59
    RunWith
    -0.59
    KommentareTeilen
    -0.57
    POSITIVE LOGITS
    umper
    0.50
    ULDER
    0.48
    illoin
    0.48
     Jovi
    0.48
    ที
    0.47
    zzar
    0.47
     aidé
    0.47
    ătă
    0.46
    ervlak
    0.46
    AxisSize
    0.46
    Activations Density 1.184%

    No Known Activations