© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91198
    Prev
    Next
    INDEX
    Explanations

    Gems or Vermont

    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
     edit
    -1.12
     edited
    -0.98
     editing
    -0.92
     editor
    -0.85
    edit
    -0.81
     Editing
    -0.81
     Editor
    -0.79
    Edited
    -0.79
     Edited
    -0.79
     Edit
    -0.78
    POSITIVE LOGITS
    principalTable
    0.66
    mobileqq
    0.53
    able
    0.51
    +#+
    0.50
     GBIF
    0.50
    Carriera
    0.49
    PerformLayout
    0.49
    imab
    0.47
    ign
    0.47
    Identyfik
    0.47
    Activations Density 0.103%

    No Known Activations