© 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. 1-CLT-HP
    7. 9292
    Prev
    Next
    INDEX
    Explanations

    less

    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
     nahilalakip
    -0.64
     OFDb
    -0.57
    oredCriteria
    -0.54
    UIControlState
    -0.54
    korn
    -0.52
    ViewFeatures
    -0.52
    tiéndose
    -0.52
    drawing
    -0.52
     }}"
    -0.50
    GraphicsUnit
    -0.50
    POSITIVE LOGITS
     demeanor
    0.53
     pilotes
    0.53
     qualities
    0.52
     Parenthood
    0.52
    wahati
    0.52
     trait
    0.52
     traits
    0.51
     motherhood
    0.51
     deeds
    0.51
     behavior
    0.51
    Activations Density 0.009%

    No Known Activations