© 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. 7046
    Prev
    Next
    INDEX
    Explanations

    references to specific genetic constructs, expression conditions, or molecular techniques

    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
     ayı
    -0.47
     surla
    -0.45
     الاطلاع
    -0.42
    ńcu
    -0.41
    PhysRev
    -0.41
    durch
    -0.40
    BatchNorm
    -0.40
    Зноскі
    -0.39
     zapew
    -0.38
    <!--[
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.71
    ReusableCell
    0.70
    principalTable
    0.69
    WireFormatLite
    0.66
    Personendaten
    0.63
    styleType
    0.63
     кӀ
    0.62
    AndroidJUnit
    0.62
    ContentAsync
    0.61
    netbeans
    0.61
    Activations Density 1.249%

    No Known Activations