© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    reports

    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
     itſelf
    -0.92
     Reſ
    -0.92
     faſt
    -0.86
     Houſe
    -0.85
     Efq
    -0.85
     myſelf
    -0.84
     Jefus
    -0.84
     Diſ
    -0.83
     purpoſe
    -0.83
     ſtate
    -0.82
    POSITIVE LOGITS
    ,
    1.21
     there
    0.78
     it
    0.76
     some
    0.73
     at
    0.66
     this
    0.65
     on
    0.65
     
    0.64
     in
    0.64
     they
    0.61
    Activations Density 0.029%

    No Known Activations