© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    words associated with asking questions and news reporting

    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
    sizeCache
    -0.59
     للمعارف
    -0.52
    pelier
    -0.48
    LVANIA
    -0.48
    صالات
    -0.47
    cedido
    -0.46
     ddelweddau
    -0.45
    достатки
    -0.45
    äumt
    -0.45
     izd
    -0.44
    POSITIVE LOGITS
     questions
    2.95
     question
    2.92
    question
    2.48
     Question
    2.48
    questions
    2.47
    Question
    2.44
     Questions
    2.42
    Questions
    2.34
     QUESTION
    2.25
     QUESTIONS
    2.19
    Activations Density 1.652%

    No Known Activations