© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10962
    Prev
    Next
    INDEX
    Explanations

    references to body weight measurements and ratios

    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
    *************/
    -0.79
    >*/
    -0.77
    </em>
    -0.76
     Carver
    -0.76
     Seitz
    -0.75
    awa
    -0.75
     Ebert
    -0.73
     Garnet
    -0.72
     fay
    -0.71
    )])
    -0.71
    POSITIVE LOGITS
     WH
    1.36
    Wh
    1.20
    Whi
    1.14
     Wharton
    1.13
     Whi
    1.11
    WH
    1.09
     Wh
    1.08
    wh
    1.08
     Whiting
    1.04
     wh
    1.02
    Activations Density 0.016%

    No Known Activations