© 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. 0-CLT-HP
    7. 42603
    Prev
    Next
    INDEX
    Explanations

    To

    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
    To
    -1.41
     To
    -1.34
     TO
    -0.96
     to
    -0.77
    ToOne
    -0.75
    to
    -0.74
     extérieures
    -0.74
     réguli
    -0.70
    ToUser
    -0.69
    ToUpdate
    -0.68
    POSITIVE LOGITS
     be
    1.20
     get
    1.05
     ensure
    1.05
     make
    1.02
     keep
    0.99
     avoid
    0.94
     protect
    0.93
     provide
    0.93
     bring
    0.91
     improve
    0.90
    Activations Density 0.104%

    No Known Activations