© 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. 97186
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    OGND
    -0.76
    日閲覧
    -0.76
     InputDecoration
    -0.76
     gynhyrchwyd
    -0.75
    Personensuche
    -0.72
    StoryboardSegue
    -0.71
    LookAnd
    -0.70
     Record
    -0.69
    ыгана
    -0.68
     Infórmanos
    -0.68
    POSITIVE LOGITS
     dieß
    0.43
    "});
    0.42
     juſ
    0.41
     ſou
    0.41
     uſ
    0.40
     themſelves
    0.40
     ―――――
    0.40
     tslint
    0.39
     myſelf
    0.39
     depositphotos
    0.38
    Activations Density 0.174%

    No Known Activations