© 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. 12-RES-MATRYOSHKA-DC
    7. 32004
    Prev
    Next
    INDEX
    Explanations

    instances of the word "impossible" and its variations expressing the concept of inability or impracticality

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    orteur
    -0.86
    CONSIN
    -0.84
    MessageOf
    -0.72
     retours
    -0.67
    Personendaten
    -0.66
    Datuak
    -0.66
    {!!
    -0.65
    pyplot
    -0.64
    vegli
    -0.63
     primaire
    -0.63
    POSITIVE LOGITS
     impossible
    0.90
     Impossible
    0.82
    impossible
    0.79
    Impossible
    0.77
    Multipart
    0.76
     Sima
    0.73
     impos
    0.70
     Gatt
    0.69
     Sart
    0.68
     WPS
    0.68
    Activations Density 0.006%

    No Known Activations