© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15716
    Prev
    Next
    INDEX
    Explanations

    company

    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
     firm
    -0.79
     kaarangay
    -0.69
     FIRM
    -0.68
    ReusableCell
    -0.67
     pinulongan
    -0.67
     rhestr
    -0.65
     Firm
    -0.62
     Firms
    -0.60
    Portail
    -0.60
    fromnode
    -0.59
    POSITIVE LOGITS
     dimenti
    0.53
     ensamb
    0.49
     kokos
    0.47
     vär
    0.46
     menyer
    0.46
    Vor
    0.45
     Vor
    0.45
    Void
    0.43
    '
    0.43
     mukaan
    0.42
    Activations Density 0.038%

    No Known Activations