© 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. 0-CLT-HP
    7. 41383
    Prev
    Next
    INDEX
    Explanations

    forms and code

    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
     
    -0.81
     O
    -0.81
      
    -0.72
     S
    -0.71
     sp
    -0.71
     a
    -0.70
    <eos>
    -0.69
     p
    -0.69
     (
    -0.69
     in
    -0.68
    POSITIVE LOGITS
     myſelf
    2.05
     Efq
    1.92
     Monfieur
    1.78
    ſelf
    1.77
     itſelf
    1.76
    ſelves
    1.72
     ―――――
    1.69
     themſelves
    1.68
     ſche
    1.65
     Theſe
    1.59
    Activations Density 0.552%

    No Known Activations