© 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. 12-RES-MATRYOSHKA-DC
    7. 17490
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prompt" and its variations in the context of a programming environment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    ècie
    -0.85
     canes
    -0.81
    SerializedName
    -0.77
     Byrne
    -0.76
    ComponentScan
    -0.75
     Carrera
    -0.71
    ‍♀
    -0.71
     Steinberg
    -0.71
     ARA
    -0.70
    lidene
    -0.70
    POSITIVE LOGITS
     prompt
    1.25
     Prompt
    1.23
    prompt
    1.10
    Prompt
    1.10
     prompts
    1.05
    PROMPT
    0.83
     promp
    0.82
     promptly
    0.81
     prompted
    0.75
     PROM
    0.70
    Activations Density 0.003%

    No Known Activations