© 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. 24-RES-MATRYOSHKA-DC
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    the word "State", and sometimes words associated with "Federal" or "Arizona"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Glej
    -0.62
    Ingestion
    -0.60
    enumii
    -0.57
    rsiniz
    -0.56
    Statement
    -0.55
    ondy
    -0.55
    copg
    -0.55
    CloseOperation
    -0.54
    binaan
    -0.52
    statement
    -0.52
    POSITIVE LOGITS
    hood
    0.92
    WIDE
    0.84
    wide
    0.80
    Wide
    0.68
     troopers
    0.66
    machine
    0.66
    HOOD
    0.66
     trooper
    0.65
     governments
    0.64
     wide
    0.62
    Activations Density 0.540%

    No Known Activations