© 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. 0-CLT-HP
    7. 45276
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    pushFollow
    -0.62
    AndEndTag
    -0.60
    subsubsection
    -0.57
    setupUi
    -0.55
    setBounds
    -0.54
     Audiodateien
    -0.54
    ContentAsync
    -0.53
    tadır
    -0.53
    glEnd
    -0.53
    </thead>
    -0.52
    POSITIVE LOGITS
    исленность
    0.71
    andExpect
    0.63
    MigrationBuilder
    0.63
     TextAppearance
    0.62
    AsUp
    0.61
    Datuak
    0.60
    TestingModule
    0.57
    CloseOperation
    0.54
    لينكات
    0.53
    ataire
    0.53
    Activations Density 1.787%

    No Known Activations