© 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. 8912
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and punctuation that indicate questioning or uncertainty

    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
     myſelf
    -0.74
     Monfieur
    -0.64
     itſelf
    -0.63
     himſelf
    -0.59
     Efq
    -0.58
     liitty
    -0.58
     Houſe
    -0.58
     juſ
    -0.57
     whoſe
    -0.57
     ſeveral
    -0.57
    POSITIVE LOGITS
    CppMethod
    0.75
    #+#
    0.68
    AddHtmlAttribute
    0.67
    abestanden
    0.65
    허
    0.65
    CDCl
    0.62
    évaluateur
    0.61
    RetentionPolicy
    0.61
     doInBackground
    0.60
    BagConstraints
    0.59
    Activations Density 0.171%

    No Known Activations