© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    words seemingly at random

    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
     plutôt
    -0.71
     both
    -0.65
     rather
    -0.63
     piuttosto
    -0.63
    rather
    -0.63
    сього
    -0.60
     autorytatywna
    -0.60
     somewhat
    -0.59
    而不是
    -0.59
     głównie
    -0.59
    POSITIVE LOGITS
     anymore
    2.33
     nor
    2.30
     any
    2.17
     anything
    1.98
    anything
    1.79
    any
    1.73
    任何
    1.72
     whatsoever
    1.72
    有任何
    1.66
     anywhere
    1.65
    Activations Density 3.928%

    No Known Activations