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. 10201
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries made in 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
    TypedDataSet
    -0.56
     erstmal
    -0.55
    makeConstraints
    -0.55
     hope
    -0.54
     kayo
    -0.53
    urgy
    -0.53
    mybatisplus
    -0.52
    뀔
    -0.52
     خارجية
    -0.51
    phany
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
     TRAD
    0.54
     plebis
    0.52
    CodeAttribute
    0.50
     dredge
    0.49
     traduire
    0.48
    enterOuterAlt
    0.48
     sekret
    0.47
    YTE
    0.47
     Pinto
    0.47
    Activations Density 0.023%

    No Known Activations