© 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. 95179
    Prev
    Next
    INDEX
    Explanations

    blog/forum content

    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
     newBuilder
    -0.47
     Gor
    -0.46
    ghum
    -0.44
     however
    -0.43
    ştir
    -0.43
    ioca
    -0.42
    Enfin
    -0.42
    ança
    -0.41
     Lo
    -0.41
    mitive
    -0.40
    POSITIVE LOGITS
    ?
    0.92
    AndEndTag
    0.91
    ?).
    0.89
    ?}
    0.84
    StoryboardSegue
    0.83
    PerformLayout
    0.82
    ?):
    0.82
    ?)
    0.82
    MigrationBuilder
    0.81
    jsxFileName
    0.79
    Activations Density 0.086%

    No Known Activations