© 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. 24-RES-MATRYOSHKA-DC
    7. 536
    Prev
    Next
    INDEX
    Explanations

    timestamps in various formats

    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.24.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.24.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
     незавершена
    -0.74
     GenerationType
    -0.69
    reportWebVitals
    -0.67
    EndInit
    -0.63
    CppCodeGen
    -0.63
    enterOuterAlt
    -0.63
    المناصب
    -0.61
     iArr
    -0.59
    клопе
    -0.59
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
     PM
    1.39
    PM
    1.34
    pm
    1.32
     pm
    1.32
     AM
    1.30
     am
    1.27
    am
    1.23
    AM
    1.20
     Pm
    0.89
    Am
    0.86
    Activations Density 0.290%

    No Known Activations