© 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. 18-RES-MATRYOSHKA-DC
    7. 393
    Prev
    Next
    INDEX
    Explanations

    "what" phrases.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    /=
    -0.69
    StructEnd
    -0.66
     invokingState
    -0.63
    reactstrap
    -0.63
    PerformLayout
    -0.61
    AutoScaleMode
    -0.60
     AssemblyCompany
    -0.60
    iastes
    -0.60
    تقاوى
    -0.60
    titleMargin
    -0.59
    POSITIVE LOGITS
    What
    0.95
     What
    0.93
     happens
    0.87
     exactly
    0.82
     do
    0.82
     händer
    0.82
     else
    0.81
     happened
    0.80
    what
    0.78
     exatamente
    0.76
    Activations Density 0.619%

    No Known Activations