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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 39
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific gradient-activation coupling related to the gradient steepness

    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
    massen
    -0.77
    verhält
    -0.74
    losigkeit
    -0.74
    chtenstein
    -0.71
    atoday
    -0.70
    öffnet
    -0.68
    fficients
    -0.67
    ionization
    -0.67
    potranspiration
    -0.67
    rechnung
    -0.66
    POSITIVE LOGITS
    -
    2.08
    ®-
    1.61
    ()-
    1.55
    ‑
    1.52
    ‐
    1.49
    -​
    1.48
    )-
    1.46
    !-
    1.37
    ]-
    1.36
    }-
    1.35
    Activations Density 3.178%

    No Known Activations