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. 19911
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or speech actions within the text

    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
     poffible
    -0.90
     ſche
    -0.88
     Roskov
    -0.86
     Forumite
    -0.84
     Efq
    -0.84
    ſelves
    -0.83
     Anſ
    -0.83
     Theſe
    -0.82
    MessageOf
    -0.82
     Majefty
    -0.82
    POSITIVE LOGITS
    ,
    0.54
     and
    0.52
    .
    0.48
    complexContent
    0.45
    ia
    0.44
    <eos>
    0.43
     El
    0.43
    author
    0.43
    velse
    0.43
    精
    0.42
    Activations Density 0.004%

    No Known Activations