© 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. 10759
    Prev
    Next
    INDEX
    Explanations

    the word "ising" which indicates a focus on "being" or "existence" in a specific context

    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
    ise
    -0.92
    +#+#
    -0.75
     TPS
    -0.66
    TPS
    -0.65
    InjectAttribute
    -0.61
     Juliette
    -0.60
    iana
    -0.57
     Italijani
    -0.57
    seitige
    -0.56
    ed
    -0.56
    POSITIVE LOGITS
    ising
    2.33
    ISING
    1.29
    IZING
    0.80
    isers
    0.68
    izing
    0.62
     nahilalakip
    0.61
    createCanvas
    0.56
    CloseOperation
    0.53
    ńcu
    0.51
    ContentAsync
    0.50
    Activations Density 0.001%

    No Known Activations