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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 32621
    Prev
    Next
    INDEX
    Explanations

    mentions of "mitogenic" entities and related terms

    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
     McGuire
    -0.84
     Waray
    -0.81
    SequentialGroup
    -0.73
    Shir
    -0.73
    Mons
    -0.73
     Gaj
    -0.71
    httphttps
    -0.71
    tagext
    -0.69
     Tare
    -0.68
    espèce
    -0.67
    POSITIVE LOGITS
     MIT
    1.59
     Mit
    1.52
     mit
    1.49
    Mit
    1.46
     Mitchell
    1.36
    mit
    1.30
    Mitch
    1.25
     MITCHELL
    1.25
    MIT
    1.24
     Mitch
    1.23
    Activations Density 0.009%

    No Known Activations