© 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. 18-RES-MATRYOSHKA-DC
    7. 126
    Prev
    Next
    INDEX
    Explanations

    statistical information

    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.18.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.18.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
    ⓧ
    -0.59
     متعلقه
    -0.59
    lccn
    -0.48
     angene
    -0.47
     VIAF
    -0.47
     IERC
    -0.46
     aujourd
    -0.44
    द्
    -0.44
    ber
    -0.44
    meld
    -0.44
    POSITIVE LOGITS
     statistically
    1.22
     statistical
    1.22
     AssemblyCulture
    1.04
    Statistical
    1.02
     statistic
    0.99
     Statistical
    0.98
    statistical
    0.92
     statisti
    0.89
     significance
    0.87
     ANOVA
    0.84
    Activations Density 8.376%

    No Known Activations