© 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. 99
    Prev
    Next
    INDEX
    Explanations

    prepositions and some related words like "whether".

    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
     он
    -0.57
     sẻ
    -0.57
     він
    -0.56
     hän
    -0.55
     vous
    -0.54
     она
    -0.54
    hasOwnProperty
    -0.53
    ترة
    -0.52
    they
    -0.50
    IT
    -0.50
    POSITIVE LOGITS
     the
    3.23
     this
    1.76
     these
    1.69
     their
    1.66
     those
    1.55
     its
    1.53
     our
    1.48
     each
    1.29
     any
    1.28
     your
    1.22
    Activations Density 13.946%

    No Known Activations