© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 281
    Prev
    Next
    INDEX
    Explanations

    words related to studies or data collection, especially in relation to following a set plan.

    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
     hindurch
    -0.73
    Identyfik
    -0.56
    CppMethod
    -0.54
    IntoConstraints
    -0.53
     sobě
    -0.52
     ProtoMessage
    -0.52
    évaluateur
    -0.52
     transfieras
    -0.52
    apnews
    -0.51
    hdessä
    -0.51
    POSITIVE LOGITS
     by
    3.08
     oleh
    2.28
    by
    1.98
     توسط
    1.73
     By
    1.67
     bởi
    1.63
    By
    1.56
     BY
    1.49
     ידי
    1.47
     przez
    1.39
    Activations Density 3.787%

    No Known Activations