© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound "ic" indicating "ionic" or "related to ions."

    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
     autorytatywna
    -0.87
    ValueStyle
    -0.75
     transfieras
    -0.71
     שוליים
    -0.71
    
    -0.69
    PullParser
    -0.66
    hound
    -0.65
     aDecoder
    -0.65
    ρους
    -0.65
    IsMutable
    -0.64
    POSITIVE LOGITS
    ic
    2.84
    IC
    2.56
    tic
    2.22
     IC
    2.13
    ics
    2.06
     ic
    2.00
    ric
    1.83
    gic
    1.69
    lic
    1.68
    onic
    1.66
    Activations Density 0.995%

    No Known Activations