© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    strings of digits and hyphens

    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
    modb
    -0.51
    tagext
    -0.48
    VideoCapture
    -0.48
    Legende
    -0.47
    stdc
    -0.47
    hbs
    -0.46
     bì
    -0.46
    ectl
    -0.46
     Picchu
    -0.46
    testify
    -0.46
    POSITIVE LOGITS
     year
    0.80
     hour
    0.68
    year
    0.67
     YEAR
    0.65
     month
    0.65
     noDo
    0.64
     dimensional
    0.63
     minute
    0.62
     Year
    0.61
     member
    0.60
    Activations Density 0.703%

    No Known Activations