© 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. 3601
    Prev
    Next
    INDEX
    Explanations

    patterns related to loop control and variable assignment

    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
     препратки
    -0.47
    行
    -0.45
     calon
    -0.42
    cls
    -0.41
    {!
    -0.41
    जे
    -0.40
    onNext
    -0.40
     modern
    -0.39
    ahhh
    -0.39
     Bue
    -0.39
    POSITIVE LOGITS
    AxisAlignment
    1.09
    tvguidetime
    0.91
    ValueGeneration
    0.90
     TextInputType
    0.86
     صوتيه
    0.85
     nahilalakip
    0.81
    TestBed
    0.79
    makeConstraints
    0.78
    bootstrapcdn
    0.76
    findpost
    0.75
    Activations Density 0.210%

    No Known Activations