© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "on" in various grammatical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    endregion
    -0.98
     useRef
    -0.85
     ElementRef
    -0.84
    出版年
    -0.78
    原始内容存档于
    -0.78
    ########.
    -0.77
    følge
    -0.77
    PreferredItem
    -0.76
    /***/
    -0.76
    исленность
    -0.76
    POSITIVE LOGITS
     on
    1.45
     On
    1.45
    On
    1.37
     ON
    1.34
     behalf
    1.30
    isOn
    1.19
    on
    1.16
     وعلى
    1.10
    setOn
    0.98
     на
    0.95
    Activations Density 2.199%

    No Known Activations