© 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. 822
    Prev
    Next
    INDEX
    Explanations

    questions beginning with the word "How"

    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
    öbb
    -0.53
    woosh
    -0.50
    IVEREF
    -0.48
     majorité
    -0.47
    Bissau
    -0.46
    amssymb
    -0.45
    VersionUID
    -0.45
    沾
    -0.45
     there
    -0.44
     vara
    -0.43
    POSITIVE LOGITS
     how
    0.96
    How
    0.91
     How
    0.90
     HOW
    0.89
     much
    0.88
     ModelExpression
    0.78
    Kako
    0.75
    Much
    0.75
    HOW
    0.73
    how
    0.71
    Activations Density 0.138%

    No Known Activations