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. 22495
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation and contributions in a discussion

    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
    riae
    -0.66
     beginnetje
    -0.65
    CAPTION
    -0.61
     تانيه
    -0.58
    IsContent
    -0.57
    TagMode
    -0.57
     consultato
    -0.56
    tagHelperRunner
    -0.56
    stdc
    -0.54
    mybatisplus
    -0.54
    POSITIVE LOGITS
    basicConfig
    0.56
    ibatis
    0.52
     vierge
    0.48
    providedIn
    0.47
    🏻
    0.44
    AndGet
    0.43
    EndContext
    0.42
    YOND
    0.42
     Asie
    0.41
     côtés
    0.41
    Activations Density 0.073%

    No Known Activations