© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    the letter X, often with other letters, numbers or symbols nearby

    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
    enumii
    -0.81
    NameInMap
    -0.74
    Gizmos
    -0.71
     PyTuple
    -0.66
    WriteTagHelper
    -0.66
    enterOuterAlt
    -0.65
    PageFactory
    -0.63
     bParam
    -0.63
    soort
    -0.63
    AddAttribute
    -0.62
    POSITIVE LOGITS
    NUMX
    0.69
     ray
    0.66
     chromosome
    0.60
    xxxxxxxxxxxxxxxx
    0.59
    xxxx
    0.59
    perience
    0.57
    press
    0.57
     axis
    0.56
    RAY
    0.56
     chromosomes
    0.55
    Activations Density 0.964%

    No Known Activations