© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    a smattering of language, not very coherent, but including words like 'worth', 'experimentation', 'Lenovo', etc.

    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
     HasFactory
    -0.59
    setImageResource
    -0.58
    략
    -0.56
    setDisable
    -0.56
    urek
    -0.54
    ჟ
    -0.54
    ুল
    -0.53
    ↵
    -0.53
    GING
    -0.53
     Réponses
    -0.53
    POSITIVE LOGITS
    ……"
    0.74
     للمعارف
    0.71
    Rptr
    0.70
     Paglinawan
    0.63
    KommentareTeilen
    0.59
    +:+
    0.58
    )];
    0.58
     ​​
    0.57
    abetes
    0.56
    تقاوى
    0.56
    Activations Density 0.581%

    No Known Activations