© 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. 6-RES-MATRYOSHKA-DC
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    negations, often involving "not" or contractions using "'t", and also words like 'the', 'so', 'is', 'to', 'in', and quantifiers.

    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
     vostri
    -0.59
    vece
    -0.53
    즉
    -0.52
     élector
    -0.50
    ValueGenerated
    -0.50
    further
    -0.49
    Dazu
    -0.49
    CodedInputStream
    -0.48
     Rpc
    -0.48
    raise
    -0.47
    POSITIVE LOGITS
     незавершена
    0.73
    requent
    0.61
    Viitteet
    0.61
    GraphicsUnit
    0.60
    Ведь
    0.57
    NamedQueries
    0.57
    SpringRunner
    0.56
     naman
    0.55
    lapsingToolbar
    0.54
     pratic
    0.54
    Activations Density 2.130%

    No Known Activations