© 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. 0-CLT-HP
    4. 43566
    Prev
    Next
    INDEX
    Explanations

    topic/question

    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
    AndEndTag
    -0.75
    Rè
    -0.69
    GEBURTSDATUM
    -0.68
     acquittal
    -0.67
    Попис
    -0.67
    bewerken
    -0.66
     Normdatei
    -0.65
     ChromeDriver
    -0.65
     purpoſe
    -0.64
     pngtree
    -0.63
    POSITIVE LOGITS
     that
    0.66
     relevant
    0.56
     like
    0.52
     about
    0.51
     such
    0.49
    <bos>
    0.47
     they
    0.47
    afy
    0.47
     previously
    0.46
    ArgsConstructor
    0.46
    Activations Density 0.076%

    No Known Activations