© 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. 654
    Prev
    Next
    INDEX
    Explanations

    words and prefixes that start with the letters "dis", "ex", "in", "ins", "sul", "conf", "ext", "des", "rep", "glam", "sq", "ee", "ee", "sq","s", "e".

    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
    ization
    -0.73
    isation
    -0.63
    sterious
    -0.59
     "}";
    -0.56
     disponibilités
    -0.54
    itisation
    -0.52
    ujan
    -0.52
    Rhestr
    -0.50
     fVar
    -0.50
    tiéndose
    -0.50
    POSITIVE LOGITS
    polate
    0.79
    tify
    0.79
    dify
    0.79
     calibrate
    0.79
    locate
    0.79
    sify
    0.78
    lify
    0.77
    ibrate
    0.76
    ify
    0.73
    uminate
    0.73
    Activations Density 0.560%

    No Known Activations