Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16912
    Prev
    Next
    INDEX
    Explanations

    monetary references and discussions about funding

    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
    Hochspringen
    -0.67
    bootstrapcdn
    -0.63
     transfieras
    -0.57
     tariff
    -0.57
     //$
    -0.56
     preghi
    -0.55
     Agamemnon
    -0.54
    Graeme
    -0.54
     ricev
    -0.53
    GetItem
    -0.53
    POSITIVE LOGITS
     CWE
    0.74
    initState
    0.61
    FieldBuilder
    0.59
     يتيمه
    0.58
     cherchés
    0.57
    ựng
    0.56
    BURG
    0.52
    Geplaatst
    0.52
     onBackPressed
    0.52
    TagHelpers
    0.51
    Activations Density 0.074%

    No Known Activations