© 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. 0-CLT-HP
    7. 43887
    Prev
    Next
    INDEX
    Explanations

    that

    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
    GEBURTSDATUM
    -0.79
    كويكب
    -0.74
     transférez
    -0.71
    AndEndTag
    -0.71
    <bos>
    -0.68
    )"
    -0.67
    staben
    -0.65
     EconPapers
    -0.65
    }}"
    -0.64
     Roskov
    -0.62
    POSITIVE LOGITS
     pleaſure
    0.61
    yntaxException
    0.59
     annul
    0.59
     feen
    0.58
     ſta
    0.56
     angelo
    0.54
    ScreenState
    0.54
     Allí
    0.54
     zugleich
    0.53
     Ofrece
    0.53
    Activations Density 0.200%

    No Known Activations