© 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. 18-RES-MATRYOSHKA-DC
    7. 203
    Prev
    Next
    INDEX
    Explanations

    discussions of politics and culture, potentially with a tone that is biased or critical

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.84
     ExecuteAsync
    -0.79
     auffi
    -0.73
    ślę
    -0.69
     peines
    -0.68
     itſelf
    -0.68
    ofern
    -0.66
    uarts
    -0.65
     ſind
    -0.64
     meilleures
    -0.64
    POSITIVE LOGITS
     propaganda
    0.89
     falsely
    0.87
     misguided
    0.85
     false
    0.81
     fake
    0.81
     hypocritical
    0.77
     blatant
    0.76
     blatantly
    0.75
     ridiculous
    0.75
     masquer
    0.75
    Activations Density 5.897%

    No Known Activations