© 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. 24-RES-MATRYOSHKA-DC
    7. 125
    Prev
    Next
    INDEX
    Explanations

    names or initials of people, often followed by a period

    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.24.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.24.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
     Second
    -0.51
     Central
    -0.49
     Original
    -0.49
     Anſ
    -0.48
     Diſ
    -0.48
     Final
    -0.47
     Mixed
    -0.46
     Reſ
    -0.46
     Perſ
    -0.45
     Special
    -0.45
    POSITIVE LOGITS
     vallée
    0.54
     van
    0.50
     Romains
    0.50
     referenties
    0.49
    citenamefont
    0.49
    IsMutable
    0.48
     propOrder
    0.47
     Duits
    0.47
     França
    0.46
     Espagne
    0.46
    Activations Density 8.891%

    No Known Activations