© 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. 12-RES-MATRYOSHKA-DC
    4. 194
    Prev
    Next
    INDEX
    Explanations

    references to anatomy or medical conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.93
     foon
    -0.88
     itſelf
    -0.87
     Majefty
    -0.84
     targeted
    -0.83
     pleaſure
    -0.82
     toolkit
    -0.82
     defire
    -0.82
     feen
    -0.81
     Jefus
    -0.81
    POSITIVE LOGITS
    faßt
    0.73
     muß
    0.69
     skall
    0.68
     läßt
    0.65
     spéciaux
    0.64
     situés
    0.63
     mußte
    0.61
     détruit
    0.61
     pesce
    0.60
     decorativos
    0.60
    Activations Density 4.435%

    No Known Activations