© 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. 91871
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    Personendaten
    -1.01
    GEBURTSDATUM
    -0.81
     AssemblyCulture
    -0.79
    6
    -0.67
    7
    -0.66
     beginnetje
    -0.65
     autorytatywna
    -0.65
    5
    -0.65
    Autoritní
    -0.60
     sclerosis
    -0.59
    POSITIVE LOGITS
    TagMode
    0.51
    NewUrlParser
    0.49
    fitriones
    0.40
    ESTRO
    0.40
     thân
    0.38
    ꞉
    0.37
    (@"%@",
    0.37
    馃
    0.36
    PANY
    0.36
     Reyn
    0.36
    Activations Density 0.008%

    No Known Activations