© 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. 6424
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "for" indicating purpose or reason

    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
    uxxxx
    -0.81
    MemoryWarning
    -0.80
    Autoritní
    -0.80
    GIVEREF
    -0.75
     Roskov
    -0.73
    Aktualisiert
    -0.72
    TagMode
    -0.71
    SequentialGroup
    -0.70
     '\\;'
    -0.70
    ensement
    -0.69
    POSITIVE LOGITS
    setupUi
    0.58
     Regarding
    0.55
    Regarding
    0.53
    โก
    0.52
     Other
    0.51
     касается
    0.50
     others
    0.50
     other
    0.49
     Others
    0.48
    Other
    0.48
    Activations Density 0.129%

    No Known Activations