© 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. 22835
    Prev
    Next
    INDEX
    Explanations

    negative values or concepts related to negativity

    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
    ValueStyle
    -1.13
     OnInit
    -0.84
     Majefty
    -0.79
     оригіналу
    -0.77
     createState
    -0.73
     Houſe
    -0.72
     تضيفلها
    -0.71
    ंदीखरीदारी
    -0.71
     tensione
    -0.68
     AppColors
    -0.68
    POSITIVE LOGITS
     mat
    0.52
    mati
    0.50
     gr
    0.49
     Kost
    0.47
    uevo
    0.46
    mew
    0.46
     r
    0.46
     l
    0.45
     lo
    0.45
     ci
    0.45
    Activations Density 0.016%

    No Known Activations