© 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. 22-RES-MATRYOSHKA-DC
    7. 2639
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    原始内容存档于
    -0.73
    Koordinaten
    -0.63
     esterni
    -0.63
    AddTagHelper
    -0.62
    DockStyle
    -0.62
    ScopeManager
    -0.60
     NKC
    -0.60
     مشين
    -0.58
     незавершена
    -0.55
     فريبيس
    -0.55
    POSITIVE LOGITS
     meet
    1.20
     met
    1.16
     Meet
    1.12
    Meet
    1.10
    meet
    1.09
     befri
    1.06
     meets
    1.05
     meeting
    1.05
     rencontre
    0.96
     interacted
    0.94
    Activations Density 0.388%

    No Known Activations