© 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. 45748
    Prev
    Next
    INDEX
    Explanations

    chromatic

    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
    chromatic
    -1.12
    ########.
    -0.78
     Roskov
    -0.77
    Corresponding
    -0.77
    InitVars
    -0.73
     betweenstory
    -0.71
    SPJ
    -0.68
    +#+#
    -0.67
    AndEndTag
    -0.66
    NOPQRST
    -0.66
    POSITIVE LOGITS
     Ri
    0.47
    CHOICES
    0.44
     Ke
    0.44
    SpringBootTest
    0.43
     Em
    0.43
     Mi
    0.43
    вік
    0.42
    อด
    0.42
     Ne
    0.41
    Males
    0.41
    Activations Density 0.401%

    No Known Activations