© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15393
    Prev
    Next
    INDEX
    Explanations

    references to bases, particularly fractional spline or wavelet bases

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.61
    [])
    
    -0.55
    cuentos
    -0.54
    //});
    -0.54
    Background
    -0.53
     retours
    -0.52
    "")
    -0.52
    ();?>
    -0.52
    umoj
    -0.51
     background
    -0.51
    POSITIVE LOGITS
     bases
    3.13
     Bases
    2.55
    bases
    2.27
    Bases
    2.08
     basses
    0.78
    StoryboardSegue
    0.76
    abases
    0.75
     nucleotides
    0.74
     AssemblyProduct
    0.70
    InjectAttribute
    0.69
    Activations Density 0.001%

    No Known Activations