© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3220
    Prev
    Next
    INDEX
    Explanations

    lists of information

    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
    regate
    -0.46
     OMITBAD
    -0.46
     orsz
    -0.44
    dres
    -0.44
    Looper
    -0.44
    Referències
    -0.43
    كتشاف
    -0.43
    MethodType
    -0.42
     neque
    -0.42
     visibilidad
    -0.42
    POSITIVE LOGITS
    TagMode
    0.67
    DeleteBehavior
    0.65
     alphabetical
    0.64
    fjspx
    0.59
     glossary
    0.58
     protoimpl
    0.56
     Scrabble
    0.55
     afp
    0.54
     GIFs
    0.54
     alphabe
    0.54
    Activations Density 0.000%

    No Known Activations