© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    input

    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
    Input
    -1.00
    input
    -0.96
     ISNI
    -0.93
     inputs
    -0.93
     Input
    -0.93
     input
    -0.86
     INPUT
    -0.85
    INPUT
    -0.84
    oredCriteria
    -0.76
    inputs
    -0.71
    POSITIVE LOGITS
    }^{+}$
    0.46
    wins
    0.44
    வே
    0.42
     yüzden
    0.42
     scene
    0.42
     tắc
    0.42
    腥
    0.42
    ngdoc
    0.41
     MonoBehaviour
    0.41
     ян
    0.40
    Activations Density 0.097%

    No Known Activations