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. 22809
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and conjunctions in the text

    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
     intptr
    -0.62
    dafrika
    -0.60
    Portale
    -0.58
    owan
    -0.57
    toThrow
    -0.57
     au
    -0.56
     speed
    -0.56
     c
    -0.55
     Vincent
    -0.54
    endregion
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.71
    bootstrapcdn
    0.70
     bezoek
    0.68
    väg
    0.67
     financière
    0.66
     själva
    0.65
    LogFactory
    0.65
    apimachinery
    0.65
    UnknownFieldSet
    0.64
    hålla
    0.63
    Activations Density 0.206%

    No Known Activations