© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2434
    Prev
    Next
    INDEX
    Explanations

    here

    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
    TagMode
    -0.64
    CppMethod
    -0.60
     disambiguazione
    -0.60
    :✨
    -0.56
    PreExecute
    -0.55
    دانشنامهٔ
    -0.53
    rigado
    -0.53
    msgTypes
    -0.52
    UnusedPrivate
    -0.51
    andExpect
    -0.50
    POSITIVE LOGITS
     automatiques
    0.56
     strøm
    0.52
     mattino
    0.49
     existência
    0.49
    Awareness
    0.48
     précédents
    0.48
    ppure
    0.47
     agrega
    0.47
    vités
    0.46
     agregar
    0.46
    Activations Density 0.005%

    No Known Activations