© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14142
    Prev
    Next
    INDEX
    Explanations

    positive emotional expressions related to love and personal reflections

    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
    者の
    -0.49
     señores
    -0.48
    pesar
    -0.48
     compréhen
    -0.47
     debout
    -0.47
     gevolg
    -0.47
    ábbi
    -0.46
     doute
    -0.46
     pauvre
    -0.46
     aéreas
    -0.46
    POSITIVE LOGITS
     Meksiku
    1.04
    IsContent
    0.98
    tvguidetime
    0.90
     שוליים
    0.88
    ViewFeatures
    0.84
    érience
    0.82
    +#+#
    0.81
     initComponents
    0.81
    parsedMessage
    0.79
    ".
    
    0.72
    Activations Density 0.891%

    No Known Activations