© 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. 1615
    Prev
    Next
    INDEX
    Explanations

    the word "leave" or "left", often followed by a short word like "to" or "the."

    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
    IntoConstraints
    -0.73
    BagLayout
    -0.73
    ところで
    -0.71
     Pingback
    -0.69
    endphp
    -0.68
    erial
    -0.68
     Incorporated
    -0.66
     متعلقه
    -0.65
    getInstance
    -0.64
    Initializable
    -0.64
    POSITIVE LOGITS
     leave
    2.75
     leaves
    2.64
     leaving
    2.52
     Leave
    2.52
    Leave
    2.47
    leave
    2.45
     Leaves
    2.44
     LEAVE
    2.44
     Leaving
    2.31
    leaves
    2.30
    Activations Density 0.251%

    No Known Activations