© 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. 1-CLT-HP
    7. 15346
    Prev
    Next
    INDEX
    Explanations

    now

    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
    andExpect
    -0.53
    BufferException
    -0.52
    stree
    -0.52
    StoryboardSegue
    -0.51
    leih
    -0.51
     TableColumn
    -0.51
     BorderLayout
    -0.51
    Tradu
    -0.51
     Touchable
    -0.49
    VersionUID
    -0.49
    POSITIVE LOGITS
    <bos>
    0.73
     Crete
    0.58
     grecque
    0.54
     Tibetan
    0.54
     abscess
    0.54
    putAll
    0.53
     woda
    0.53
    ⓧ
    0.53
     Forscher
    0.53
     astronomers
    0.52
    Activations Density 0.012%

    No Known Activations