© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1456
    Prev
    Next
    INDEX
    Explanations

    instances of stating opinions or thinking, especially using "I" or "we."

    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/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyTitle
    -0.72
     <<<<<<<<<<<<<<
    -0.69
     estekak
    -0.64
    DockStyle
    -0.63
    ьаж
    -0.61
    prüche
    -0.61
     виправивши
    -0.61
     Audiodateien
    -0.60
     Mentioned
    -0.58
     فريبيس
    -0.57
    POSITIVE LOGITS
     believe
    1.16
     think
    1.03
     suspect
    0.94
     doubt
    0.88
     believes
    0.86
    believe
    0.85
    think
    0.79
     thinks
    0.72
     creen
    0.70
     view
    0.70
    Activations Density 0.704%

    No Known Activations