© 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. 1056
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
     Paglinawan
    -0.77
    <bos>
    -0.70
     ✭✭
    -0.69
    contentLoaded
    -0.69
     Envío
    -0.67
    DockStyle
    -0.66
     itſelf
    -0.66
    OGND
    -0.64
     ——
    -0.63
    Carriera
    -0.60
    POSITIVE LOGITS
     مرئيه
    0.45
    urlpatterns
    0.42
    />
    0.40
    ])]
    0.40
    ]])
    0.38
    ➯
    0.37
    "/>
    0.37
    ();*/
    0.36
     hoang
    0.36
    /)
    0.35
    Activations Density 0.010%

    No Known Activations