© 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. 0-CLT-HP
    7. 42423
    Prev
    Next
    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -1.02
     termica
    -1.02
     avoient
    -0.99
     engraçadas
    -0.98
     feroit
    -0.97
     femininos
    -0.96
     étoient
    -0.92
    OGND
    -0.92
     femininas
    -0.91
     متعلقه
    -0.91
    POSITIVE LOGITS
     black
    0.58
     white
    0.57
     old
    0.57
     little
    0.55
    ,
    0.55
     part
    0.54
     red
    0.54
     top
    0.54
     land
    0.53
     non
    0.52
    Activations Density 0.037%

    No Known Activations