© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    longitude

    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
    :✨
    -0.52
     surla
    -0.52
     potuto
    -0.52
    TagMode
    -0.51
    <bos>
    -0.50
    '&:
    -0.49
    sw
    -0.49
    parken
    -0.49
     Verhält
    -0.48
    eddable
    -0.48
    POSITIVE LOGITS
    CodedInputStream
    0.83
    StackNavigator
    0.63
    ReusableCell
    0.60
    })->
    0.57
    enderror
    0.56
    WebServlet
    0.55
    DispatchToProps
    0.55
    nologue
    0.52
    getSeconds
    0.52
     SqlCommand
    0.52
    Activations Density 0.001%

    No Known Activations