© 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. 3867
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Datuak
    -0.54
    DoubleQuotes
    -0.51
     phthal
    -0.47
    łasz
    -0.47
    FXML
    -0.47
     initComponents
    -0.45
    kust
    -0.44
    ServletException
    -0.43
    IndentedString
    -0.43
     sheets
    -0.42
    POSITIVE LOGITS
    kháu
    0.68
    preuve
    0.60
     nature
    0.59
    ミナル
    0.58
    omyia
    0.56
    ugía
    0.54
    Personensuche
    0.54
    oa̍t
    0.53
    igslist
    0.53
     evidence
    0.53
    Activations Density 0.003%

    No Known Activations