© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    the word "based" followed by certain words

    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
     Ginn
    -0.69
    اهرة
    -0.67
    pyplot
    -0.67
    StringWriter
    -0.67
     Winfrey
    -0.65
     WALT
    -0.64
    ervé
    -0.64
     caoutchouc
    -0.64
    beo
    -0.63
     Schia
    -0.63
    POSITIVE LOGITS
     Based
    1.72
     based
    1.70
    Based
    1.70
     bases
    1.63
    BASED
    1.63
    based
    1.62
     BASED
    1.60
     basing
    1.53
     Bases
    1.48
    Bases
    1.45
    Activations Density 0.576%

    No Known Activations