© 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. 3693
    Prev
    Next
    INDEX
    Explanations

    the concept of being in a kernel or null space

    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
     Réponses
    -0.64
    Izvori
    -0.60
    antwoorde
    -0.57
     moeite
    -0.56
    číta
    -0.55
    
    -0.55
     Calais
    -0.54
    JPL
    -0.54
    円
    -0.54
    firi
    -0.53
    POSITIVE LOGITS
    ker
    3.94
    KER
    3.13
     ker
    2.84
    Ker
    2.64
     Ker
    2.56
    kers
    2.33
     KER
    2.23
    keri
    1.73
    keren
    1.61
    kerne
    1.56
    Activations Density 0.014%

    No Known Activations