© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44222
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    ❋
    -0.64
     محفوظة
    -0.63
    mybatisplus
    -0.58
    LLocation
    -0.57
    //
    -0.57
    :✨
    -0.56
    sinon
    -0.56
     CanadaChoose
    -0.55
    enumi
    -0.54
    dk
    -0.54
    POSITIVE LOGITS
     rigging
    0.57
     Gallimard
    0.55
     avoient
    0.54
     célè
    0.52
     Monfieur
    0.52
    Rij
    0.51
     rugs
    0.50
     fédé
    0.50
    leby
    0.50
     réfrig
    0.50
    Activations Density 0.630%

    No Known Activations