© 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. 327
    Prev
    Next
    INDEX
    Explanations

    examples and caveats.

    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
     purpoſe
    -0.81
     Diſ
    -0.79
     raiſ
    -0.77
     ſeveral
    -0.77
     ſub
    -0.76
     doInBackground
    -0.74
     preſent
    -0.72
     Anſ
    -0.72
     Reſ
    -0.70
     houſe
    -0.70
    POSITIVE LOGITS
     like
    1.51
    like
    1.40
     Like
    1.38
    Like
    1.29
     LIKE
    1.24
     bijvoorbeeld
    1.16
    LIKE
    1.13
     likes
    1.13
    voorbeeld
    1.12
     zoals
    1.11
    Activations Density 1.367%

    No Known Activations