© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15363
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emphasis or intensity

    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
    bit
    -0.86
    Bit
    -0.85
     lot
    -0.85
    BIT
    -0.83
     Bit
    -0.83
    Bits
    -0.83
     Bits
    -0.81
    Lot
    -0.72
     BITS
    -0.71
    tvguidetime
    -0.70
    POSITIVE LOGITS
    somewhat
    0.61
    slightly
    0.60
     Etwas
    0.59
    reh
    0.59
    ι
    0.57
     somewhat
    0.57
     slightly
    0.56
    Somewhat
    0.56
     etwas
    0.56
    httphttps
    0.54
    Activations Density 0.009%

    No Known Activations