© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3804
    Prev
    Next
    INDEX
    Explanations

    to

    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
    LookAnd
    -0.79
    NOPQRST
    -0.75
    +#+#
    -0.69
     đỡ
    -0.67
    StoryboardSegue
    -0.66
    savevideo
    -0.65
     StringTokenizer
    -0.65
    quisite
    -0.64
    Хьажоргаш
    -0.63
    SourceChecksum
    -0.63
    POSITIVE LOGITS
     StatelessWidget
    0.45
     sèche
    0.43
     règles
    0.43
    Len
    0.42
     ciudadana
    0.41
    idavit
    0.40
     poursu
    0.40
    lec
    0.40
     rapides
    0.40
     lunares
    0.39
    Activations Density 0.001%

    No Known Activations