© 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. 16804
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and."

    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
    AnimationsModule
    -0.60
    InputTagHelper
    -0.58
     aquilo
    -0.58
     rien
    -0.57
     bezeichneter
    -0.57
     climatisation
    -0.57
    HomeAsUpEnabled
    -0.56
    WebElementEntity
    -0.56
     كومونز
    -0.55
    formik
    -0.55
    POSITIVE LOGITS
     tagName
    0.61
     concatenation
    0.55
    habitants
    0.54
     pank
    0.54
    meanor
    0.53
    sterna
    0.53
    wollen
    0.52
     skr
    0.52
     Heu
    0.52
    handlebars
    0.52
    Activations Density 0.033%

    No Known Activations