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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19656
    Prev
    Next
    INDEX
    Explanations

    clarifications or affirmations in statements

    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
     artificiales
    -0.50
     piped
    -0.49
     plă
    -0.48
     GenerationType
    -0.47
     çev
    -0.46
     educativas
    -0.46
     căr
    -0.46
    せっかく
    -0.46
    transQ
    -0.46
     însă
    -0.45
    POSITIVE LOGITS
    abinieri
    0.68
     تضيفلها
    0.68
    MigrationBuilder
    0.66
    zzleHttp
    0.64
    expandindo
    0.63
    qrstuvwxyz
    0.59
    arques
    0.58
    openzeppelin
    0.58
    protoimpl
    0.57
    arschu
    0.57
    Activations Density 0.052%

    No Known Activations