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. 16961
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing further information or definitions

    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
     nahilalakip
    -0.81
     onOptions
    -0.76
    RectangleBorder
    -0.73
     typelib
    -0.71
     Audiodateien
    -0.69
     detail
    -0.69
    MLLoader
    -0.66
    Bronnen
    -0.65
    protoimpl
    -0.64
     дописавши
    -0.62
    POSITIVE LOGITS
     passively
    0.53
     passive
    0.50
    Personendaten
    0.50
    perk
    0.49
    .
    0.48
    Clasificación
    0.48
     maar
    0.47
     való
    0.45
     färg
    0.45
     Swartz
    0.44
    Activations Density 0.025%

    No Known Activations