© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15273
    Prev
    Next
    INDEX
    Explanations

    descriptions of mathematical transforms and their properties

    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
     compétence
    -0.52
    kann
    -0.50
    PWR
    -0.47
     detenidos
    -0.45
     stabilité
    -0.44
     elecciones
    -0.43
    察
    -0.43
    hånd
    -0.42
    Propel
    -0.41
     Osiris
    -0.41
    POSITIVE LOGITS
    onomía
    0.75
    醐
    0.65
    argout
    0.64
     OFDb
    0.64
    
    0.64
    asko
    0.61
    Népesség
    0.60
    варь
    0.60
     Meksiku
    0.59
    slidesToShow
    0.59
    Activations Density 0.014%

    No Known Activations