© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and references, particularly those containing the substring "ineq".

    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
    ness
    -0.90
    root
    -0.68
    road
    -0.68
    으로
    -0.64
    right
    -0.63
    scan
    -0.63
    d
    -0.62
    screen
    -0.62
    roots
    -0.62
    ship
    -0.61
    POSITIVE LOGITS
    eeee
    0.66
    eee
    0.66
    EEEE
    0.60
    eeeeee
    0.57
    EEEEEE
    0.56
    eeeee
    0.56
    ek
    0.54
    e
    0.53
    eeeeeeee
    0.53
    yntaxException
    0.52
    Activations Density 0.914%

    No Known Activations