© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to the concept of history and duration of time

    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
     MainAxisSize
    -0.82
    |}{$
    -0.81
    MigrationBuilder
    -0.81
    oredCriteria
    -0.75
     للاسماء
    -0.73
    érfi
    -0.73
    Vidite
    -0.73
    protoimpl
    -0.72
     Normdatei
    -0.72
     Италијани
    -0.70
    POSITIVE LOGITS
     until
    3.77
    until
    3.28
     till
    3.27
     Until
    3.14
    Until
    3.14
     UNTIL
    2.88
     hasta
    2.80
     untill
    2.78
     jusqu
    2.72
    Till
    2.56
    Activations Density 1.526%

    No Known Activations