© 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. 5-CLT-HP
    7. 91732
    Prev
    Next
    INDEX
    Explanations

    Code and text fragments

    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
     nakalista
    -0.76
     Италијани
    -0.64
    providedIn
    -0.59
     linkovi
    -0.56
     Meksiku
    -0.52
    richTextPanel
    -0.52
     forState
    -0.50
    Personendaten
    -0.50
     in
    -0.49
    HostException
    -0.49
    POSITIVE LOGITS
     tracks
    0.74
    tracks
    0.64
     itſelf
    0.63
     its
    0.63
     pleaſure
    0.62
     purpoſe
    0.60
     greateſt
    0.57
     leſs
    0.57
     track
    0.56
     uſed
    0.56
    Activations Density 0.002%

    No Known Activations