© 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. 3-RES-MATRYOSHKA-DC
    7. 2401
    Prev
    Next
    INDEX
    Explanations

    the word "latter"

    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
     Early
    -0.67
    Early
    -0.67
     sil
    -0.64
    EARLY
    -0.63
     dieux
    -0.62
     EARLY
    -0.62
    finally
    -0.61
     Finally
    -0.61
     early
    -0.60
    early
    -0.59
    POSITIVE LOGITS
     latter
    2.36
    latter
    1.78
    后者
    1.65
     Latter
    1.27
     thereof
    0.98
    OGND
    0.81
     letz
    0.78
     former
    0.77
     senare
    0.74
    DoubleQuotes
    0.73
    Activations Density 0.011%

    No Known Activations