© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    the character å

    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
    awtextra
    -0.87
    ræ
    -0.75
    æ
    -0.73
     &___
    -0.73
    RTDA
    -0.72
    /**
    -0.71
    Tikang
    -0.70
     nakalista
    -0.70
    ="#"><
    -0.67
     Wikimédia
    -0.64
    POSITIVE LOGITS
    å
    2.47
    åt
    0.99
    åd
    0.99
    år
    0.96
    ål
    0.93
    ått
    0.93
    Å
    0.91
    åk
    0.90
     å
    0.82
    åg
    0.81
    Activations Density 0.006%

    No Known Activations