© 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. 5793
    Prev
    Next
    INDEX
    Explanations

    Halloween

    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
    RefNanny
    -0.48
    >');
    -0.45
     pinulongan
    -0.44
    AccessorTable
    -0.42
     file
    -0.42
    ')")
    -0.42
    /}.
    -0.42
    gés
    -0.40
    bors
    -0.40
     glycerol
    -0.40
    POSITIVE LOGITS
    ContentAsync
    0.64
    +#+
    0.60
     considérons
    0.59
     يتيمه
    0.58
    yntaxException
    0.58
     AppColors
    0.57
     raiſ
    0.56
     Theſe
    0.56
    WebpackPlugin
    0.56
    Carcinogenicity
    0.56
    Activations Density 0.001%

    No Known Activations