© 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. 195
    Prev
    Next
    INDEX
    Explanations

    names of people along with surrounding words

    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
     pinulongan
    -0.72
     calendriers
    -0.59
     autorytatywna
    -0.58
     famí
    -0.57
     HasFactory
    -0.57
     GetEnumerator
    -0.56
    ::*;
    -0.55
     kaarangay
    -0.54
    ();*/
    -0.52
    ReadByte
    -0.52
    POSITIVE LOGITS
     विश्वसनीयता
    0.79
     الدولى
    0.60
    bootstrapcdn
    0.59
    SOUNDBITE
    0.56
    cupertino
    0.53
    mybatisplus
    0.50
     спря
    0.50
     RSSSF
    0.49
     ComVisible
    0.49
    openConnection
    0.48
    Activations Density 13.722%

    No Known Activations