© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96621
    Prev
    Next
    INDEX
    Explanations

    cannot/not

    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
     &___
    -0.62
    gnings
    -0.56
    inginan
    -0.54
    AFE
    -0.54
    apatalk
    -0.54
    webElementGuid
    -0.54
    arnings
    -0.53
    nalités
    -0.51
    hauer
    -0.51
    ningss
    -0.51
    POSITIVE LOGITS
    Have
    0.68
     Have
    0.60
     have
    0.59
    have
    0.59
    enderror
    0.58
     exist
    0.57
     Exist
    0.56
    Exist
    0.52
     exis
    0.51
    󠁴
    0.51
    Activations Density 0.021%

    No Known Activations