© 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. 2-RES-MATRYOSHKA-DC
    7. 4499
    Prev
    Next
    INDEX
    Explanations

    expressions of the contraction "I've" indicating personal experience or affirmation

    oai_token-act-pair · gpt-4.1-nano
    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
    antMatchers
    -0.81
    tagHelperRunner
    -0.75
    terase
    -0.73
    Personensuche
    -0.67
     flakes
    -0.66
    ///</
    -0.66
    ьаж
    -0.65
    IUrlHelper
    -0.65
    abank
    -0.65
    Tikang
    -0.65
    POSITIVE LOGITS
    ve
    1.87
     ve
    1.41
    VE
    1.23
     Ve
    1.21
    Ve
    1.13
     VE
    1.02
    Ive
    0.96
     ive
    0.93
     Ive
    0.91
    ive
    0.76
    Activations Density 0.031%

    No Known Activations