© 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. 1-CLT-HP
    7. 13854
    Prev
    Next
    INDEX
    Explanations

    Biochemistry and neuroscience

    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
     gyrus
    -1.16
    DockStyle
    -0.71
    发表于
    -0.57
    vda
    -0.56
     Ngb
    -0.56
    makeConstraints
    -0.54
     Jansen
    -0.52
    actéristiques
    -0.50
    VIAF
    -0.49
    igslist
    -0.49
    POSITIVE LOGITS
     Wortes
    0.63
     financières
    0.62
    OrNil
    0.61
     mourut
    0.60
     vectorielles
    0.59
     médicale
    0.58
    abello
    0.57
     ritorno
    0.56
     silenzio
    0.56
     provisoire
    0.54
    Activations Density 0.440%

    No Known Activations