© 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. 18480
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or contemplation

    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
     laugh
    -0.50
     κύ
    -0.49
    уза
    -0.49
     đại
    -0.48
     Resp
    -0.48
    setScene
    -0.46
     senior
    -0.46
    TRAILING
    -0.45
    endsection
    -0.44
    ,
    -0.43
    POSITIVE LOGITS
     myſelf
    1.05
     Efq
    1.01
     Monfieur
    0.90
     hmm
    0.85
     Hmm
    0.81
    WireFormatLite
    0.81
    ſelf
    0.80
     againſt
    0.79
     himſelf
    0.78
     itſelf
    0.78
    Activations Density 0.011%

    No Known Activations