© 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. 22-RES-MATRYOSHKA-DC
    7. 1379
    Prev
    Next
    INDEX
    Explanations

    references to armies or armies, particularly in a historical context.

    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.22.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.22.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
    alina
    -0.45
    שמי
    -0.42
    piso
    -0.41
    ratto
    -0.40
    ζα
    -0.40
     offici
    -0.40
     zak
    -0.40
     Polri
    -0.40
    ন্ত
    -0.40
    ISTOL
    -0.40
    POSITIVE LOGITS
     attacking
    1.06
     reinforcements
    1.02
     attack
    0.98
     attaque
    0.90
     victory
    0.89
     defeat
    0.88
     besie
    0.87
    attack
    0.86
     siege
    0.85
     attacked
    0.85
    Activations Density 1.220%

    No Known Activations