© 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. 15220
    Prev
    Next
    INDEX
    Explanations

    references to user preferences and options related to website cookies, settings, or configuration choices

    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
     preference
    -1.02
    Preference
    -0.83
     Preference
    -0.81
     prefer
    -0.76
     Prefer
    -0.75
    prefer
    -0.74
    Prefer
    -0.71
    preference
    -0.67
     emphasis
    -0.63
     priorité
    -0.62
    POSITIVE LOGITS
    preferences
    1.50
     Preferences
    1.38
     preferences
    1.29
    Preferences
    1.21
    principalColumn
    0.75
     سكانية
    0.67
    anskje
    0.66
     autorytatywna
    0.64
     ویکی‌پدیای
    0.59
     tastes
    0.59
    Activations Density 0.001%

    No Known Activations