Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14576
    Prev
    Next
    INDEX
    Explanations

    references to technical details related to the extrapolation or estimation of numerical or physical parameters

    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
    nEnter
    -0.58
     članak
    -0.56
    posedge
    -0.55
    withIdentifier
    -0.54
    őd
    -0.53
    sschule
    -0.52
    clerview
    -0.51
    semibold
    -0.50
     Multipart
    -0.50
     wzgl
    -0.50
    POSITIVE LOGITS
     extrapolation
    1.16
     extrapolated
    0.97
     McDowell
    0.75
     totality
    0.71
    Threading
    0.71
    moy
    0.71
     disambiguazione
    0.69
    (;;)
    0.69
    Lähteet
    0.69
    BRA
    0.67
    Activations Density 0.069%

    No Known Activations