© 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. 488
    Prev
    Next
    INDEX
    Explanations

    clauses conjoined to 'and' or 'to', often containing personal pronouns or prepositions

    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
     asim
    -0.65
    )()
    -0.62
    ModelBuilder
    -0.61
    стероид
    -0.58
    IRING
    -0.56
     tromper
    -0.55
    mitteln
    -0.54
    enschaft
    -0.54
     visita
    -0.54
     λά
    -0.54
    POSITIVE LOGITS
     grabbed
    0.80
     grab
    0.73
     tug
    0.73
     crouched
    0.72
     grabbing
    0.72
     yank
    0.71
     grabs
    0.70
     yelled
    0.69
    grab
    0.68
     berdiri
    0.68
    Activations Density 1.390%

    No Known Activations