© 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. 500
    Prev
    Next
    INDEX
    Explanations

    words related to knowing, wondering, and telling as well as the prepositions that connect them

    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
    IMDG
    -0.60
     समीक्षक
    -0.60
    ghis
    -0.58
    yaszt
    -0.54
    }$_
    -0.54
    Portale
    -0.54
    GOTREF
    -0.54
    好不容易
    -0.53
    íritu
    -0.52
    tså
    -0.52
    POSITIVE LOGITS
     how
    3.02
     what
    2.30
     why
    2.20
     whether
    2.11
    how
    1.93
     where
    1.73
     cómo
    1.72
     bagaimana
    1.68
    what
    1.60
     who
    1.59
    Activations Density 2.829%

    No Known Activations