© 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. 15406
    Prev
    Next
    INDEX
    Explanations

    phrases expressing perceptions or opinions regarding the status of subjects

    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
     grazia
    -0.62
     hâte
    -0.58
    нрави
    -0.57
     AppCompatTheme
    -0.56
    ТЕЛЬ
    -0.56
    வர்
    -0.56
     Misses
    -0.55
    madan
    -0.55
    Способ
    -0.55
     acoper
    -0.55
    POSITIVE LOGITS
     regarded
    0.75
     trataba
    0.73
     Barbour
    0.72
     trak
    0.69
    LabelTagHelper
    0.67
    fjspx
    0.66
     treated
    0.65
    WithIOException
    0.64
    multer
    0.63
    MemoryWarning
    0.63
    Activations Density 0.047%

    No Known Activations