© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17577
    Prev
    Next
    INDEX
    Explanations

    negations and terms indicating a counter perspective or disagreement

    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
    Personensuche
    -0.66
     "..\..\..\
    -0.63
    DebuggerNonUser
    -0.57
     "..\..\
    -0.57
    +#+#
    -0.56
    IndentedString
    -0.56
    invokeLater
    -0.54
    Diweddarwch
    -0.52
    DebuggerStep
    -0.51
    TProtocol
    -0.50
    POSITIVE LOGITS
     myſelf
    0.85
     firſt
    0.81
     Theſe
    0.81
     Majefty
    0.80
     photolibrary
    0.78
     himſelf
    0.77
     itſelf
    0.77
     Monfieur
    0.77
     Anſ
    0.75
     ſhe
    0.75
    Activations Density 0.121%

    No Known Activations