© 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. 4-CLT-HP
    7. 858
    Prev
    Next
    INDEX
    Explanations

    Wondering/questions

    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
    +#+#
    -0.79
    новниш
    -0.65
     getItemCount
    -0.60
    Diweddarwch
    -0.60
     transfieras
    -0.59
    IBOutlet
    -0.58
     cherchés
    -0.56
    protoimpl
    -0.54
    initializeApp
    -0.53
    GIVEREF
    -0.53
    POSITIVE LOGITS
    fully
    0.56
    ably
    0.48
     strøm
    0.46
    ally
    0.45
    ostro
    0.45
    ed
    0.44
    opolis
    0.43
    istin
    0.42
    ically
    0.42
    transQ
    0.42
    Activations Density 0.001%

    No Known Activations