© 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. 91476
    Prev
    Next
    INDEX
    Explanations

    lead

    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
     plegable
    -0.61
     igång
    -0.60
     fidèles
    -0.60
     noires
    -0.58
     to
    -0.58
     vendeurs
    -0.57
     enseignants
    -0.57
     hydrauli
    -0.56
     députés
    -0.56
     ingår
    -0.56
    POSITIVE LOGITS
     the
    0.65
    AMENTE
    0.54
    ########.
    0.53
    AndEndTag
    0.52
    ьаж
    0.49
    esModule
    0.46
    LOAT
    0.46
     hides
    0.46
    🏻
    0.46
    Alike
    0.45
    Activations Density 0.001%

    No Known Activations