© 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. 0-RES-MATRYOSHKA-DC
    7. 11944
    Prev
    Next
    INDEX
    Explanations

    dimensions related to maximum values, emphasizing the identification of the highest or peak metrics

    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
     Min
    -1.18
    Min
    -1.05
    NameInMap
    -0.75
    uxxxx
    -0.73
    oredCriteria
    -0.65
     تضيفلها
    -0.62
     insuffisamment
    -0.60
     AssemblyCulture
    -0.59
    TemporalType
    -0.58
    assertArray
    -0.56
    POSITIVE LOGITS
    MAX
    1.85
     MAX
    1.54
    readyState
    0.73
    LEncoder
    0.69
    maxim
    0.67
    Portail
    0.65
     maxim
    0.63
     Maxim
    0.63
    prnt
    0.61
    Maxim
    0.60
    Activations Density 0.002%

    No Known Activations