© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2811
    Prev
    Next
    INDEX
    Explanations

    of

    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
     argint
    -0.59
    ellites
    -0.52
     Freien
    -0.51
    antMatchers
    -0.50
    abstractmethod
    -0.50
    dden
    -0.49
    thoven
    -0.49
    izr
    -0.48
    hsv
    -0.48
     parallèle
    -0.48
    POSITIVE LOGITS
    SqlSession
    0.52
    曖昧さ回避
    0.50
    ьаж
    0.50
    Britannique
    0.49
    AndEndTag
    0.49
    InitVars
    0.48
    SBATCH
    0.48
     الحره
    0.47
    Poloha
    0.47
     deployment
    0.47
    Activations Density 0.002%

    No Known Activations