© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    questions and dialogues in discussions or interviews

    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
     kaarangay
    -0.81
     calendriers
    -0.79
     Италијани
    -0.76
    AndEndTag
    -0.75
     esternos
    -0.66
     متعلقه
    -0.64
     препратки
    -0.63
    abestanden
    -0.62
    curkan
    -0.62
     EconPapers
    -0.60
    POSITIVE LOGITS
     questions
    0.93
     perguntas
    0.84
     domande
    0.79
     question
    0.77
     interviewer
    0.74
     preguntas
    0.73
     interrog
    0.72
    Пита
    0.70
     interviewers
    0.70
    質問
    0.69
    Activations Density 0.123%

    No Known Activations