© 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. 20-CLT-HP
    7. 75765
    Prev
    Next
    INDEX
    Explanations

    project, explain

    np_max-act-logits · 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
    
    -0.91
    AndEndTag
    -0.84
     незавершена
    -0.77
     defaultstate
    -0.69
    TagMode
    -0.67
    BeginContext
    -0.66
     raccolta
    -0.65
    bootstrapcdn
    -0.64
    ########.
    -0.63
     pleaſure
    -0.61
    POSITIVE LOGITS
     present
    0.57
     Project
    0.57
    providedIn
    0.55
     project
    0.54
     explain
    0.53
     throw
    0.52
     drive
    0.51
     justify
    0.51
    Project
    0.50
    tiel
    0.49
    Activations Density 0.000%

    No Known Activations