© 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. 6-RES-MATRYOSHKA-DC
    7. 153
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific or technical research

    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
    amını
    -0.62
     
    -0.62
    اااا
    -0.53
     ģ
    -0.52
    ocene
    -0.52
    conium
    -0.52
     مرئيه
    -0.50
    **********/
    -0.49
    glicher
    -0.49
     côtes
    -0.49
    POSITIVE LOGITS
    oa̍t
    0.87
    withstanding
    0.83
    Manbalar
    0.82
    SerializedSize
    0.80
    GEBURTSDATUM
    0.78
    ThemeOverlay
    0.77
    NUMX
    0.76
    writeFieldEnd
    0.76
    CrossRef
    0.75
    etheless
    0.74
    Activations Density 5.254%

    No Known Activations