© 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. 102
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to chemical processes and substances

    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
    ,
    -1.06
     (
    -0.98
     
    -0.98
    :
    -0.97
    <eos>
    -0.97
    .
    -0.89
    /
    -0.85
    ↵↵
    -0.85
     =
    -0.85
    ;
    -0.84
    POSITIVE LOGITS
    ſelves
    1.50
    neſs
    1.43
    ſelf
    1.41
    IBLIO
    1.38
     ſind
    1.31
    ſem
    1.28
     raiſ
    1.28
     $_"
    1.24
     BRARY
    1.23
     photolibrary
    1.23
    Activations Density 6.465%

    No Known Activations