© 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. 2-RES-MATRYOSHKA-DC
    7. 6707
    Prev
    Next
    INDEX
    Explanations

    references to personal attitudes or opinions about specific topics

    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
    at
    -0.45
    ia
    -0.45
     
    -0.43
    p
    -0.43
    f
    -0.43
    du
    -0.41
    V
    -0.41
     survie
    -0.40
    -
    -0.40
    v
    -0.40
    POSITIVE LOGITS
     HasFactory
    1.04
     Monfieur
    1.00
     defaultstate
    0.99
    WebVitals
    0.98
     EconPapers
    0.96
    EDEFAULT
    0.96
     autorytatywna
    0.96
    ImageContext
    0.94
    Personendaten
    0.93
    featureID
    0.92
    Activations Density 1.701%

    No Known Activations