© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2641
    Prev
    Next
    INDEX
    Explanations

    academic/scientific writing

    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
    fromnode
    -0.45
     bagay
    -0.43
     And
    -0.41
    ArgsConstructor
    -0.40
    <eos>
    -0.40
    ValueOf
    -0.40
     Lovato
    -0.39
    Dou
    -0.39
     onBackPressed
    -0.38
     on
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.97
     Theſe
    0.75
     myſelf
    0.69
     ſeveral
    0.69
     Houſe
    0.68
     contextLoads
    0.67
     kaarangay
    0.66
     neceffary
    0.65
     itſelf
    0.65
    ]='\
    0.64
    Activations Density 0.007%

    No Known Activations