© 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. 161
    Prev
    Next
    INDEX
    Explanations

    testimonies related to statements made during legal proceedings

    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
    Espèce
    -0.67
    ByteBuf
    -0.65
     AGM
    -0.60
    ANNES
    -0.57
     actionTypes
    -0.56
    vety
    -0.56
    Демографія
    -0.54
    hedrals
    -0.51
    IUrlHelper
    -0.51
     mums
    -0.50
    POSITIVE LOGITS
    帖最后由
    0.60
     did
    0.59
     AspNetCore
    0.59
     volna
    0.58
     allegedly
    0.57
     was
    0.57
     complained
    0.56
     told
    0.56
     ويكيپيديا
    0.56
     verbally
    0.55
    Activations Density 4.714%

    No Known Activations