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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4707
    Prev
    Next
    INDEX
    Explanations

    technical/research documents

    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
     related
    -0.61
     specific
    -0.60
     others
    -0.59
     certain
    -0.59
     modern
    -0.55
     different
    -0.53
     also
    -0.52
     other
    -0.51
     such
    -0.51
     specifically
    -0.51
    POSITIVE LOGITS
    Personendaten
    1.44
     فريبيس
    1.28
     صوتيه
    1.22
    rungsseite
    1.19
    expandindo
    1.18
    tagHelperRunner
    1.13
    DockStyle
    1.09
    Datuak
    1.09
     nahilalakip
    1.09
     مرئيه
    1.08
    Activations Density 0.144%

    No Known Activations