© 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. 377
    Prev
    Next
    INDEX
    Explanations

    substrings that look like identifiers or codes

    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
    BITE
    -0.74
     ttt
    -0.71
    EDE
    -0.67
    tete
    -0.65
    OTA
    -0.64
    ELLE
    -0.63
     fff
    -0.63
     MEND
    -0.63
    AGA
    -0.63
    FEA
    -0.63
    POSITIVE LOGITS
     leçon
    0.68
     vicenda
    0.65
     pensée
    0.62
     coppia
    0.61
     complètes
    0.60
     appunto
    0.59
     scoperta
    0.59
     nélkül
    0.59
     coscienza
    0.59
     femininas
    0.57
    Activations Density 3.853%

    No Known Activations