© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23249
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" in various contexts, indicating descriptions or attributes

    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
    Negative Logits
    úgó
    -0.70
    DllImport
    -0.66
    IERRA
    -0.66
    ⓧ
    -0.65
    écnicas
    -0.64
    ientôt
    -0.64
    UnusedPrivate
    -0.64
    cetto
    -0.63
     Cuen
    -0.62
    PreAuthorize
    -0.62
    POSITIVE LOGITS
     tartalomajánló
    0.57
     الحره
    0.53
     Wikimedijinoj
    0.52
    fjspx
    0.52
    <bos>
    0.50
    parsedMessage
    0.50
     fieldNum
    0.50
    swig
    0.49
    раздо
    0.48
    DebuggerNonUser
    0.46
    Activations Density 0.086%

    No Known Activations