© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 859
    Prev
    Next
    INDEX
    Explanations

    expressions of love, enjoyment, preference and appreciation.

    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
     münd
    -0.63
     permission
    -0.62
    EndContext
    -0.62
    FormTagHelper
    -0.61
     allowed
    -0.60
    {\$
    -0.59
    áus
    -0.55
     @"/
    -0.54
    ElementException
    -0.54
     asked
    -0.54
    POSITIVE LOGITS
     love
    2.73
     LOVE
    2.48
    love
    2.39
     Love
    2.36
    LOVE
    2.31
    Love
    2.25
     loves
    2.25
    loves
    2.16
     loved
    2.08
    loved
    1.98
    Activations Density 0.445%

    No Known Activations