© 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. 163
    Prev
    Next
    INDEX
    Explanations

    references to articles or publications

    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
    ConstraintMaker
    -0.57
     operating
    -0.56
    arange
    -0.56
    range
    -0.53
    AreEqual
    -0.53
    thenReturn
    -0.53
    CMAKE
    -0.53
    NameValuePair
    -0.52
    帖最后由
    -0.52
    imageshack
    -0.52
    POSITIVE LOGITS
     manuscript
    1.46
     manuscripts
    1.40
     books
    1.18
     writings
    1.17
     documents
    1.13
     article
    1.12
     writer
    1.12
     articles
    1.11
     writers
    1.09
     published
    1.08
    Activations Density 3.534%

    No Known Activations