© 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. 45467
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Mel
    -0.54
     Mark
    -0.44
     and
    -0.43
     for
    -0.43
     I
    -0.43
     Mass
    -0.42
     int
    -0.41
     fa
    -0.41
     p
    -0.41
    WireFormatLite
    -0.40
    POSITIVE LOGITS
    ſelf
    1.25
     Majefty
    1.23
    ſelves
    1.21
     itſelf
    1.21
     Monfieur
    1.21
     Houſe
    1.20
     raiſ
    1.18
     Anſ
    1.18
     myſelf
    1.16
     Efq
    1.16
    Activations Density 0.156%

    No Known Activations