© 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. 92820
    Prev
    Next
    INDEX
    Explanations

    This

    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
     This
    -1.38
     These
    -0.74
     It
    -0.65
    This
    -0.63
     THIS
    -0.59
     The
    -0.58
     Its
    -0.58
     If
    -0.56
     There
    -0.55
     That
    -0.54
    POSITIVE LOGITS
     is
    1.30
     makes
    0.91
    DeleteBehavior
    0.90
     reflects
    0.89
     was
    0.89
     applies
    0.88
     doesn
    0.86
     has
    0.86
     isn
    0.85
     happens
    0.85
    Activations Density 0.138%

    No Known Activations