© 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. 3-RES-MATRYOSHKA-DC
    7. 1060
    Prev
    Next
    INDEX
    Explanations

    the fraction one half

    oai_token-act-pair · gemini-2.0-flash
    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
    tagHelperRunner
    -0.71
    homonymie
    -0.69
    msgTypes
    -0.65
     InputDecoration
    -0.63
     безу
    -0.58
    Begriffsklä
    -0.57
    igno
    -0.57
    CIR
    -0.57
    siem
    -0.57
    astru
    -0.57
    POSITIVE LOGITS
     Half
    0.66
     AssemblyCulture
    0.66
    Half
    0.63
    half
    0.60
     half
    0.56
    IsPostBack
    0.54
     termica
    0.53
     ogóle
    0.53
     Hälfte
    0.52
     spagnolo
    0.52
    Activations Density 0.408%

    No Known Activations