© 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. 15180
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "mis-" indicating a wrong or erroneous state

    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
     StatefulWidget
    -0.93
    AndEndTag
    -0.93
     كمان
    -0.91
    horabuena
    -0.91
    ⓧ
    -0.90
    InputBorder
    -0.86
     BorderRadius
    -0.85
    ьаж
    -0.83
    ModelAttribute
    -0.82
     protoimpl
    -0.82
    POSITIVE LOGITS
     MIS
    1.45
     mis
    1.34
     Mis
    1.27
    Mis
    1.27
    mis
    1.24
    MIS
    1.21
     miso
    0.78
    Missi
    0.77
     mismatch
    0.75
     Miscell
    0.74
    Activations Density 0.026%

    No Known Activations