© 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. 12-RES-MATRYOSHKA-DC
    7. 14334
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    AutoField
    -0.62
     HasFactory
    -0.56
     these
    -0.51
     TestBed
    -0.50
    defineProperty
    -0.50
     accesso
    -0.50
    égard
    -0.49
     AssemblyTitle
    -0.49
     go
    -0.47
    +/**
    -0.45
    POSITIVE LOGITS
     мәкал
    0.68
     Riverdale
    0.68
    Gambas
    0.67
    énieurs
    0.66
     lordship
    0.64
     Lordship
    0.63
     Paglinawan
    0.63
    QMetaType
    0.63
     Shakspeare
    0.63
     greate
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.