© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43669
    Prev
    Next
    INDEX
    Explanations

    goals

    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
     goals
    -1.67
    goals
    -1.28
     Goals
    -1.22
    Goals
    -1.13
     concerns
    -1.10
     dreams
    -1.03
     GOALS
    -1.02
     desires
    -0.97
     hopes
    -0.91
     worries
    -0.88
    POSITIVE LOGITS
    omeness
    0.57
     précédents
    0.53
    __*/
    0.52
     extérieurs
    0.50
    ณ์
    0.49
    haped
    0.47
    cripts
    0.46
     lèvres
    0.45
     transferir
    0.44
     commandé
    0.44
    Activations Density 0.073%

    No Known Activations