© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14727
    Prev
    Next
    INDEX
    Explanations

    values associated with experimental or statistical data

    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
    -0.85
    findpost
    -0.77
     otomatig
    -0.76
     <=",
    -0.76
     gynhyrchwyd
    -0.74
     ProtoMessage
    -0.71
    ValueStyle
    -0.71
    MigrationBuilder
    -0.69
    Хьажоргаш
    -0.68
     صوتيه
    -0.68
    POSITIVE LOGITS
     purpoſe
    0.56
     Recogn
    0.51
     pleaſure
    0.51
     Nau
    0.50
    gros
    0.50
     Piv
    0.49
     Sols
    0.48
    olon
    0.47
     reaſon
    0.47
    Instru
    0.47
    Activations Density 0.003%

    No Known Activations