© 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. 4937
    Prev
    Next
    INDEX
    Explanations

    expressions of negation or denial

    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
    AnimationsModule
    -0.72
    IconModule
    -0.59
    ătoare
    -0.58
    ActionPerformed
    -0.54
    ্ন
    -0.52
    CROSSTALK
    -0.52
    ariats
    -0.51
    ioutil
    -0.50
    béco
    -0.50
     additionally
    -0.49
    POSITIVE LOGITS
    InvalidProtocol
    0.69
     AspNetCore
    0.60
    sidemargin
    0.60
     udaler
    0.59
    klü
    0.59
     kimdir
    0.58
    исленность
    0.57
    viel
    0.56
     aint
    0.56
    γωγ
    0.56
    Activations Density 0.333%

    No Known Activations