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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14530
    Prev
    Next
    INDEX
    Explanations

    references to the concept of infinite or endless quantity

    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
     kasarigan
    -0.53
    プーン
    -0.51
    frequency
    -0.50
     רח
    -0.50
    Cuánto
    -0.50
    𝘅
    -0.49
    xic
    -0.48
    override
    -0.47
    awesome
    -0.47
     reverend
    -0.47
    POSITIVE LOGITS
     endless
    2.58
     Endless
    2.36
    endless
    2.17
    Endless
    2.11
     unending
    1.32
     endlessly
    1.26
     countless
    1.23
     interminable
    1.13
    无尽
    1.02
     intermin
    0.99
    Activations Density 0.003%

    No Known Activations