Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 31937
    Prev
    Next
    INDEX
    Explanations

    addresses and location details within a text

    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
     للاسماء
    -0.85
     وتسجيلات
    -0.80
    ConstraintMaker
    -0.79
     Paglinawan
    -0.75
    IntoConstraints
    -0.65
    SequentialGroup
    -0.60
    makeConstraints
    -0.59
    fjspx
    -0.59
    qrstuvwxyz
    -0.58
    AddTagHelper
    -0.57
    POSITIVE LOGITS
    AsUp
    0.61
    zió
    0.51
    iniums
    0.45
    autant
    0.45
     bounced
    0.44
     конферен
    0.44
    RELATION
    0.44
    EndProject
    0.43
    FirstResponder
    0.42
     Suite
    0.42
    Activations Density 0.004%

    No Known Activations