© 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. 411
    Prev
    Next
    INDEX
    Explanations

    clauses in historical narrative sentences

    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
     purpoſe
    -0.66
     Sopho
    -0.64
     Monfieur
    -0.63
     Cæsar
    -0.62
     Gallimard
    -0.60
     Jefus
    -0.59
     brome
    -0.57
     myſelf
    -0.56
     foon
    -0.56
     occaf
    -0.56
    POSITIVE LOGITS
     @"/
    0.71
    UnsafeEnabled
    0.68
    Ӕ
    0.67
    σαι
    0.62
     portátiles
    0.62
    oredCriteria
    0.61
     HasFactory
    0.60
     decorativos
    0.59
    WebpackPlugin
    0.58
     كورة
    0.58
    Activations Density 2.737%

    No Known Activations