© 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. 3-RES-MATRYOSHKA-DC
    7. 2133
    Prev
    Next
    INDEX
    Explanations

    words containing the characters å or Ä

    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
     Hopf
    -0.63
    CodedInputStream
    -0.59
     diarrhoea
    -0.57
    setVerticalGroup
    -0.55
     organisations
    -0.54
     Kategor
    -0.54
     CGPA
    -0.54
    EnableWeb
    -0.53
    )++;
    -0.53
     emphasise
    -0.53
    POSITIVE LOGITS
     æ
    1.50
     ä
    1.12
    LEncoder
    0.69
    ThroughAttribute
    0.69
     محفوظة
    0.68
     Ä
    0.66
     newBuilder
    0.61
    ביוגרפיה
    0.60
    TemporalType
    0.59
    ViewFeatures
    0.58
    Activations Density 0.010%

    No Known Activations