© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10573
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hide."

    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
    Negative Logits
    hide
    -1.23
    Hide
    -0.81
    HIDE
    -0.64
    RegistryLite
    -0.63
     TextAppearance
    -0.61
    URLException
    -0.59
     Hid
    -0.58
    slideUp
    -0.56
     venons
    -0.55
    kiel
    -0.55
    POSITIVE LOGITS
     hide
    1.44
     hides
    0.85
    DockStyle
    0.68
    Scénario
    0.61
     FormBuilder
    0.53
    ollectionView
    0.52
    initWithFrame
    0.52
    bufio
    0.51
    WriteAttribute
    0.51
    PhysRevLett
    0.51
    Activations Density 0.002%

    No Known Activations