© 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. 26683
    Prev
    Next
    INDEX
    Explanations

    references to scientific research related to hormonal changes and attraction

    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
     AssemblyCulture
    -0.80
    KURZBESCHREIBUNG
    -0.78
     HasFactory
    -0.77
    énario
    -0.76
    yntaxException
    -0.75
     للاسماء
    -0.74
    principalTable
    -0.73
    oredCriteria
    -0.73
    Havolalar
    -0.69
     AssemblyCompany
    -0.68
    POSITIVE LOGITS
     activation
    0.54
     hormone
    0.52
    &__
    0.50
     моз
    0.48
     Dijk
    0.47
     brain
    0.47
     trigger
    0.46
     primitive
    0.46
    Encoding
    0.45
     kích
    0.45
    Activations Density 0.122%

    No Known Activations