© 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. 1831
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "some", "states", "countries", "warranty", "above", "itation", and "ions" in a single phrase or sentence

    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
    Clik
    -0.64
    acaktır
    -0.62
    <bos>
    -0.57
    __':
    -0.53
    なんですが
    -0.53
    __":
    -0.53
    Hauptartikel
    -0.52
    页面存档备份
    -0.49
    extAlignment
    -0.47
     externi
    -0.46
    POSITIVE LOGITS
     may
    3.14
     might
    2.92
    may
    2.66
    might
    2.52
     Might
    2.31
    Might
    2.28
     MAY
    2.28
    May
    2.09
     May
    2.06
     MIGHT
    2.02
    Activations Density 1.366%

    No Known Activations