© 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. 3-RES-MATRYOSHKA-DC
    7. 2392
    Prev
    Next
    INDEX
    Explanations

    angle brackets that often precede or follow structured data such as code

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.97
     itſelf
    -0.73
    IntoConstraints
    -0.70
    parametrize
    -0.69
    bronn
    -0.68
     OMITBAD
    -0.68
     faſt
    -0.67
    wnętr
    -0.66
    věr
    -0.66
     Theſe
    -0.66
    POSITIVE LOGITS
     <
    1.79
     (<
    1.01
    (<
    0.94
     >
    0.91
     >=
    0.90
    "><
    0.79
    ><
    0.76
     <=
    0.75
     <<
    0.71
    ///<
    0.71
    Activations Density 0.045%

    No Known Activations