© 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. 2875
    Prev
    Next
    INDEX
    Explanations

    the beginning or end of German city names.

    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
    HomeAsUpEnabled
    -0.74
    HostException
    -0.71
    Portály
    -0.67
    Initializable
    -0.63
    RenderAtEndOf
    -0.63
     didat
    -0.63
    )‏
    -0.63
    rzez
    -0.61
     JoJo
    -0.61
    Sle
    -0.61
    POSITIVE LOGITS
     Wald
    3.06
    Wald
    2.70
    wald
    2.56
     wald
    2.00
     Waldorf
    1.19
     forest
    1.02
    forest
    0.99
     Forest
    0.96
    Forest
    0.96
     Forests
    0.95
    Activations Density 0.001%

    No Known Activations