© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    programming questions / answers

    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
    ImageContext
    -0.66
    awtextra
    -0.58
    évaluateur
    -0.53
    ocarditis
    -0.53
    NGC
    -0.53
     wants
    -0.52
    XmlIgnore
    -0.52
    ogonal
    -0.51
    hassee
    -0.50
    ⎨
    -0.50
    POSITIVE LOGITS
    Likely
    0.62
     canst
    0.51
    signOut
    0.49
     stride
    0.49
     Louvain
    0.48
     Likely
    0.47
     Мексичка
    0.47
    EndTag
    0.46
     inferiority
    0.46
    Able
    0.45
    Activations Density 0.091%

    No Known Activations