© 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. 19235
    Prev
    Next
    INDEX
    Explanations

    double quotation marks or related punctuation

    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
     محفوظة
    -0.74
     propOrder
    -0.71
     ‘‘
    -0.63
     “
    -0.61
    thâu
    -0.58
    Geplaatst
    -0.57
     ‘
    -0.57
    quelize
    -0.56
    rungsseite
    -0.56
    Matchers
    -0.55
    POSITIVE LOGITS
    ;");
    0.60
     CanadaChoose
    0.58
    וויק
    0.58
    Біографія
    0.54
    ("]");
    0.54
    Rhestr
    0.53
    FromNib
    0.52
    ử
    0.52
    brainly
    0.51
    */)
    0.51
    Activations Density 0.041%

    No Known Activations