© 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. 1-CLT-HP
    7. 12948
    Prev
    Next
    INDEX
    Explanations

    import

    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
    ThroughAttribute
    -0.60
    Hochspringen
    -0.58
     utafitiHapana
    -0.54
    liesslich
    -0.54
     Nein
    -0.53
    }();
    -0.52
     Scene
    -0.52
    </thead>
    -0.51
     triton
    -0.50
    \}\\
    -0.50
    POSITIVE LOGITS
     виправивши
    0.58
    LabelTagHelper
    0.56
    TypedDataSet
    0.55
    TagHelper
    0.55
    QMetaType
    0.53
    writerow
    0.50
     esboço
    0.50
     ComVisible
    0.50
     nakalista
    0.50
     صوتيه
    0.49
    Activations Density 1.961%

    No Known Activations