© 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. 92034
    Prev
    Next
    INDEX
    Explanations

    websites or crisis

    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
     inf
    -0.63
     cent
    -0.60
    новништво
    -0.50
    JECT
    -0.50
     sik
    -0.49
     pan
    -0.48
    ########.
    -0.47
     saites
    -0.47
    lium
    -0.47
    athione
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.85
     trasparente
    0.79
    <bos>
    0.76
     auroit
    0.69
     Etr
    0.69
     itſelf
    0.69
     sportiva
    0.68
     ainfi
    0.68
    ="@+
    0.67
     akong
    0.67
    Activations Density 0.179%

    No Known Activations