© 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. 44089
    Prev
    Next
    INDEX
    Explanations

    indeed

    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
     indeed
    -1.59
    indeed
    -1.41
    Indeed
    -1.13
     inderdaad
    -1.09
     Indeed
    -1.07
     notes
    -1.00
     effectivement
    -0.98
    certainly
    -0.95
     ciertamente
    -0.93
     infatti
    -0.89
    POSITIVE LOGITS
    .
    0.59
    ,
    0.51
    :
    0.51
    发表于
    0.50
    !
    0.49
    Revenir
    0.46
     >
    0.45
    >>
    0.45
    yn
    0.44
     exists
    0.44
    Activations Density 0.377%

    No Known Activations