© 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. 22-RES-MATRYOSHKA-DC
    7. 2860
    Prev
    Next
    INDEX
    Explanations

    the preposition "of" and words closely associated with it.

    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.22.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.22.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
    -
    -0.63
    Is
    -0.52
    1
    -0.49
    ;
    -0.47
    (
    -0.47
    .
    -0.46
    ,
    -0.46
     study
    -0.45
    ↵
    -0.44
    2
    -0.44
    POSITIVE LOGITS
     Италијани
    1.02
     disambiguazione
    0.97
    IntoConstraints
    0.96
    ...")
    0.94
     otomatig
    0.93
     Italijani
    0.92
    ...')
    0.91
    IndentedString
    0.91
    Personensuche
    0.91
     kasarigan
    0.90
    Activations Density 0.272%

    No Known Activations