© 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. 91020
    Prev
    Next
    INDEX
    Explanations

    undesirable

    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
     gene
    -0.98
     interests
    -0.92
    ly
    -0.84
     interested
    -0.77
     interesting
    -0.73
    gene
    -0.73
     Gene
    -0.71
     undesirable
    -0.65
    interests
    -0.65
    sounds
    -0.65
    POSITIVE LOGITS
     AssemblyProduct
    0.75
    cluye
    0.61
     noires
    0.60
    DOCTYPE
    0.60
     igång
    0.59
     Wicidata
    0.58
    HostException
    0.57
    +#+
    0.56
    mphony
    0.56
    ništ
    0.56
    Activations Density 0.136%

    No Known Activations