© 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. 1365
    Prev
    Next
    INDEX
    Explanations

    periods followed by a number

    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
     betweenstory
    -0.98
     autorytatywna
    -0.84
     Meksiku
    -0.74
    InstrumentedTest
    -0.69
    Jeografia
    -0.69
     ivelany
    -0.67
     tartalomajánló
    -0.63
    Brainz
    -0.60
     /\.
    -0.59
     experto
    -0.56
    POSITIVE LOGITS
    resolvers
    0.63
     الحره
    0.63
    pidou
    0.62
    alties
    0.58
     Obrador
    0.57
    ův
    0.56
     JADX
    0.56
    στ
    0.56
    glColor
    0.55
     campur
    0.55
    Activations Density 0.679%

    No Known Activations