Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15176
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and inclusion conditions

    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
    Atsauces
    -0.54
    Cubit
    -0.53
    deviantart
    -0.50
    org
    -0.48
     sẻ
    -0.47
    ISupport
    -0.45
    AxisAlignment
    -0.45
     населён
    -0.45
     volna
    -0.45
     concorso
    -0.44
    POSITIVE LOGITS
    PhysRevD
    0.64
     cherchés
    0.63
     تكبرها
    0.59
    JHEP
    0.57
    WHM
    0.57
    PMailer
    0.56
     Heine
    0.56
    phosa
    0.55
    GenerationType
    0.54
     travaillons
    0.53
    Activations Density 0.001%

    No Known Activations