© 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. 15326
    Prev
    Next
    INDEX
    Explanations

    references to software licensing or legal notices

    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
     كومونز
    -1.00
     Reſ
    -0.99
     itſelf
    -0.98
     Eſ
    -0.90
    yntaxException
    -0.90
     Conſ
    -0.88
     EconPapers
    -0.88
     myſelf
    -0.88
    المكان
    -0.86
     Theſe
    -0.85
    POSITIVE LOGITS
     Software
    1.53
    Software
    1.20
    SOFTWARE
    0.68
     So
    0.48
     an
    0.47
     SOFTWARE
    0.47
     (
    0.44
    ----------------
    0.44
    ote
    0.44
     und
    0.43
    Activations Density 0.002%

    No Known Activations