© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 891
    Prev
    Next
    INDEX
    Explanations

    the terms "high" or "low" as adjectives

    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
    #+#
    -0.79
    uttgart
    -0.74
     easier
    -0.73
    StructEnd
    -0.72
     BIBSYS
    -0.72
     Exacts
    -0.68
     Exactos
    -0.68
     Mako
    -0.67
    easier
    -0.66
    تقاوى
    -0.63
    POSITIVE LOGITS
     high
    2.59
    high
    2.52
     High
    2.44
    High
    2.41
     HIGH
    2.14
    HIGH
    2.13
     low
    2.08
     Low
    2.06
    Low
    2.00
    low
    1.88
    Activations Density 0.687%

    No Known Activations