© 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. 5949
    Prev
    Next
    INDEX
    Explanations

    technical terms related to algebraic geometry and schemes

    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
    setRotation
    -0.58
    FontOfSize
    -0.56
     incomplète
    -0.54
    LookAnd
    -0.53
    ********/
    -0.52
     salariés
    -0.49
     sorella
    -0.49
    ->___
    -0.48
    vres
    -0.47
    userdetails
    -0.47
    POSITIVE LOGITS
     androidx
    0.72
     فريبيس
    0.65
     algebraic
    0.57
     Algebraic
    0.56
    TagMode
    0.55
     dekol
    0.55
     Hypers
    0.55
     OnTriggerEnter
    0.54
    findpost
    0.54
    ímite
    0.53
    Activations Density 0.560%

    No Known Activations