© 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. 91607
    Prev
    Next
    INDEX
    Explanations

    governing bodies

    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
    HOLE
    -0.59
    windowFixed
    -0.59
    gdx
    -0.59
    xla
    -0.57
    Lago
    -0.56
    洞
    -0.56
    GEBURTS
    -0.55
     district
    -0.55
     nakalista
    -0.54
    wns
    -0.53
    POSITIVE LOGITS
     виправивши
    0.51
    MethodManager
    0.49
    StructEnd
    0.45
    DrawerToggle
    0.45
     Body
    0.44
     onlyOwner
    0.43
    jami
    0.43
     '\\;'
    0.43
    Бахар
    0.42
    jetbrains
    0.41
    Activations Density 0.009%

    No Known Activations