© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I," indicating a focus on personal experiences or opinions

    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
    rungsseite
    -0.93
    RefNanny
    -0.79
     myſelf
    -0.77
    NewUrlParser
    -0.74
    AddressBook
    -0.73
    下载附件
    -0.68
     CURIAM
    -0.68
     дописавши
    -0.68
    ForValue
    -0.67
    WriteBarrier
    -0.67
    POSITIVE LOGITS
    ↵
    0.58
     it
    0.47
     little
    0.47
     is
    0.44
    rrggbb
    0.44
     
    0.44
    aarrggbb
    0.43
    ↵↵
    0.43
     in
    0.43
     effect
    0.43
    Activations Density 0.028%

    No Known Activations