© 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. 6-RES-MATRYOSHKA-DC
    7. 343
    Prev
    Next
    INDEX
    Explanations

    the word "some" followed by a determiner or adjective.

    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
    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
    AutoScaleMode
    -0.84
    MigrationBuilder
    -0.84
    LookAnd
    -0.80
    Kjelder
    -0.77
    何より
    -0.77
    AfterClass
    -0.76
     ApiException
    -0.71
     MessageBoxIcon
    -0.70
     оригіналу
    -0.69
     cockroach
    -0.68
    POSITIVE LOGITS
     some
    1.85
    SOME
    1.80
    some
    1.72
     SOME
    1.72
    Some
    1.69
     Some
    1.59
     Algunos
    1.30
     Certains
    1.27
     Alguns
    1.27
     algunos
    1.25
    Activations Density 0.703%

    No Known Activations