© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1055
    Prev
    Next
    INDEX
    Explanations

    Ordinal numbers

    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
     verdaderos
    -0.45
    len
    -0.44
    st
    -0.43
    th
    -0.43
    igne
    -0.40
    wi
    -0.40
    nn
    -0.40
     verdadera
    -0.39
    multicolumn
    -0.39
    ert
    -0.39
    POSITIVE LOGITS
    ScopeManager
    0.94
    expandindo
    0.91
    MigrationBuilder
    0.86
     &___
    0.83
     continúas
    0.80
     defaultstate
    0.80
     Normdatei
    0.78
    CppMethod
    0.77
    AndEndTag
    0.77
    +#+#
    0.76
    Activations Density 0.026%

    No Known Activations