© 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. 6389
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to system errors and state changes in a programming context

    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
     Osiris
    -0.38
     examples
    -0.38
    书记
    -0.37
     soccer
    -0.36
     Sacchar
    -0.36
     electrocardio
    -0.36
     Garuda
    -0.35
     fili
    -0.34
     Chairperson
    -0.34
     Svizzera
    -0.34
    POSITIVE LOGITS
    providedIn
    0.78
    pushFollow
    0.78
     estekak
    0.74
    TagMode
    0.73
     defaultstate
    0.69
     发表于
    0.68
    BeginContext
    0.68
    windowFixed
    0.68
    scriptId
    0.68
    principalColumn
    0.67
    Activations Density 0.185%

    No Known Activations