© 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. 28533
    Prev
    Next
    INDEX
    Explanations

    negative numerical values or symbols associated with negativity

    oai_token-act-pair · gpt-4o-mini
    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
     GenerationType
    -0.81
     onData
    -0.81
    idać
    -0.76
    IUrlHelper
    -0.74
    fillType
    -0.73
    SharedCtor
    -0.72
    WithIOException
    -0.72
     AssemblyTitle
    -0.71
     pinulongan
    -0.71
    GEBURTSDATUM
    -0.71
    POSITIVE LOGITS
    Demografia
    0.65
     کیلومتر
    0.54
    Ouch
    0.50
    koľ
    0.49
     naturales
    0.47
    autoFocus
    0.47
    ichen
    0.46
    zzata
    0.46
     cherchez
    0.45
    ifu
    0.45
    Activations Density 0.037%

    No Known Activations