© 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. 4-CLT-HP
    7. 1259
    Prev
    Next
    INDEX
    Explanations

    having

    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
     afast
    -0.53
     skjer
    -0.51
    ard
    -0.50
    тература
    -0.50
    var
    -0.49
     ruote
    -0.48
    amssymb
    -0.47
    ști
    -0.47
    chin
    -0.47
     lontano
    -0.47
    POSITIVE LOGITS
     esternos
    0.77
     interviewed
    0.71
    extAlignment
    0.66
     interview
    0.63
     Spisak
    0.61
     للاسماء
    0.60
    CodedInputStream
    0.58
     flown
    0.57
     difficulty
    0.57
     waited
    0.57
    Activations Density 0.002%

    No Known Activations