© 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. 845
    Prev
    Next
    INDEX
    Explanations

    references to years

    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
    AndEndTag
    -0.98
     Efq
    -0.74
    Hochspringen
    -0.73
     Theſe
    -0.71
    matchCondition
    -0.70
    tonsoft
    -0.69
     مشين
    -0.68
     goutte
    -0.68
    MetaObject
    -0.67
    SuppressMessage
    -0.66
    POSITIVE LOGITS
     lenker
    0.72
    ANTLR
    0.51
    Cama
    0.47
     BE
    0.46
     externi
    0.44
    заи
    0.44
     eben
    0.43
     kaj
    0.43
    avra
    0.43
    becher
    0.42
    Activations Density 0.672%

    No Known Activations