© 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. 26489
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of doubt or regret

    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
     itſelf
    -1.02
     Anſ
    -0.94
     pleaſure
    -0.93
     myſelf
    -0.88
     Majefty
    -0.85
     виправивши
    -0.84
     Jefus
    -0.83
     fhew
    -0.81
    enderror
    -0.79
     anſ
    -0.79
    POSITIVE LOGITS
     so
    0.54
     for
    0.53
     COVID
    0.52
     I
    0.50
     fact
    0.50
     COMPONENT
    0.49
    COVID
    0.47
     na
    0.47
    PyErr
    0.46
     che
    0.46
    Activations Density 0.014%

    No Known Activations