© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14084
    Prev
    Next
    INDEX
    Explanations

    references to citations or references

    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
     مرئيه
    -0.88
     naught
    -0.77
     Normdatei
    -0.75
    atimes
    -0.73
    venidos
    -0.69
     éché
    -0.68
     виправивши
    -0.67
    lapsingToolbar
    -0.66
    expandindo
    -0.65
    xase
    -0.65
    POSITIVE LOGITS
    ,[
    2.05
    },[
    0.69
    jooq
    0.65
    â
    0.58
    ​​
    0.55
    RequestBuilder
    0.52
     اس
    0.51
    ,{
    0.50
     â
    0.50
    ',['
    0.50
    Activations Density 0.001%

    No Known Activations