© 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. 24-RES-MATRYOSHKA-DC
    7. 122
    Prev
    Next
    INDEX
    Explanations

    people (who, everyone), groups of people (we, They, lawmakers, Founders), and companies ("Allbritton Communications Company")

    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.24.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.24.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
     constitutes
    -0.57
     itſelf
    -0.57
     arisen
    -0.56
    
    -0.55
     serem
    -0.54
    檚
    -0.53
    tonsoft
    -0.52
    AsUp
    -0.52
    TextAppearance
    -0.52
    ToMany
    -0.52
    POSITIVE LOGITS
    '
    1.30
     knew
    1.21
     know
    1.19
     want
    1.19
    ’
    1.17
     wanted
    1.14
     KNOW
    1.08
     think
    1.04
     didn
    0.99
     knows
    0.98
    Activations Density 4.198%

    No Known Activations