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. 30572
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about origins and reasons

    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
    unier
    -0.51
    étaro
    -0.49
    zków
    -0.49
    liac
    -0.48
    amina
    -0.47
    ekse
    -0.47
    chlag
    -0.45
     Mieter
    -0.45
    牝
    -0.45
     plan
    -0.44
    POSITIVE LOGITS
     مشين
    0.71
    Etimo
    0.71
    ########.
    0.68
    MarshalTo
    0.68
    ">//
    0.64
    :✨
    0.61
    IntoConstraints
    0.60
     препратки
    0.59
     откуда
    0.58
    endphp
    0.58
    Activations Density 0.104%

    No Known Activations