© 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. 2453
    Prev
    Next
    INDEX
    Explanations

    references to spectral analysis and related concepts

    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
     оригіналу
    -0.98
    HasAnnotation
    -0.93
    omla
    -0.89
    sizeCache
    -0.87
     Javan
    -0.87
     homoto
    -0.85
    Personendaten
    -0.85
    niająca
    -0.82
    InjectMocks
    -0.81
     DriverManager
    -0.77
    POSITIVE LOGITS
     spectra
    1.59
     Spectrum
    1.51
     Spectra
    1.47
    Spectrum
    1.45
     spectrum
    1.36
    spectrum
    1.34
    Spect
    1.31
    spectra
    1.30
     SPECT
    1.20
     Spect
    1.09
    Activations Density 0.060%

    No Known Activations