© 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. 766
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to oneself or others

    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
    Geplaatst
    -0.60
     jelas
    -0.58
     certainly
    -0.57
     Chwiliwch
    -0.56
    I
    -0.56
     invitamos
    -0.54
     also
    -0.53
    We
    -0.53
     probably
    -0.53
     vastaan
    -0.52
    POSITIVE LOGITS
     समीक्षाओं
    0.73
    Tikang
    0.70
    関連項目
    0.69
    ualla
    0.69
     BaseActivity
    0.68
     sandero
    0.67
    EReference
    0.67
    ^(@)
    0.66
    bibitem
    0.66
    scienced
    0.66
    Activations Density 0.688%

    No Known Activations